Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.7916. Min Act: -0.1700
Data Index: 4901400 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.6979. Min Act: -0.1700
Data Index: 3533104 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.6979. Min Act: -0.1698
Data Index: 5233332 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.6979. Min Act: -0.1700
Data Index: 7735133 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.6666. Min Act: -0.1700
Data Index: 2756902 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.6041. Min Act: -0.1700
Data Index: 6512534 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.6041. Min Act: -0.1700
Data Index: 3854914 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.6041. Min Act: -0.1700
Data Index: 1466173 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.6041. Min Act: -0.1700
Data Index: 7040685 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.5729. Min Act: -0.1700
Data Index: 1471251 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.5729. Min Act: -0.1700
Data Index: 8623031 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.5729. Min Act: -0.1700
Data Index: 1703589 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.5416. Min Act: -0.1700
Data Index: 266404 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.5104. Min Act: -0.1700
Data Index: 8524990 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.5104. Min Act: -0.1700
Data Index: 1466160 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.5104. Min Act: -0.1700
Data Index: 2065615 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.5104. Min Act: -0.1700
Data Index: 3146417 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.5104. Min Act: -0.1700
Data Index: 5010958 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.4791. Min Act: -0.1700
Data Index: 2861450 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7916. Min Range: -5.7916
Max Act: 5.4791. Min Act: -0.1700
Data Index: 1466167 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19