Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1731 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.0468. Min Range: -11.0468
Max Act: 11.0468. Min Act: -0.1700
Data Index: 1612542 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.9843. Min Act: -0.1700
Data Index: 6891929 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.8593. Min Act: -0.1700
Data Index: 172726 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.7968. Min Act: -0.1700
Data Index: 2753082 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.7968. Min Act: -0.1700
Data Index: 8278648 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.7343. Min Act: -0.1700
Data Index: 5367688 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.6718. Min Act: -0.1700
Data Index: 6512757 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.7343. Min Act: -0.1700
Data Index: 1627131 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.7968. Min Act: -0.1700
Data Index: 4081261 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.6718. Min Act: -0.1700
Data Index: 3190086 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.6718. Min Act: -0.1700
Data Index: 5303084 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.6718. Min Act: -0.1700
Data Index: 1909272 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.6718. Min Act: -0.1700
Data Index: 6159278 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.6718. Min Act: -0.1700
Data Index: 3426911 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.6093. Min Act: -0.1700
Data Index: 6268882 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.5468. Min Act: -0.1700
Data Index: 173040 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.5468. Min Act: -0.1700
Data Index: 5021813 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.5468. Min Act: -0.1700
Data Index: 297235 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.5468. Min Act: -0.1700
Data Index: 4326247 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0468. Min Range: -11.0468
Max Act: 10.5468. Min Act: -0.1700
Data Index: 3102073 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19