Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 24 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.7969. Min Act: -0.1700
Data Index: 7669187 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.5781. Min Act: -0.1700
Data Index: 6206706 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.6094. Min Act: -0.1700
Data Index: 7336642 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.5781. Min Act: -0.1700
Data Index: 245563 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.5781. Min Act: -0.1700
Data Index: 1720666 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.5156. Min Act: -0.1700
Data Index: 6634730 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.5156. Min Act: -0.1700
Data Index: 12575 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.5156. Min Act: -0.1700
Data Index: 717738 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.4844. Min Act: -0.1700
Data Index: 6436280 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.4844. Min Act: -0.1700
Data Index: 385311 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.4844. Min Act: -0.1700
Data Index: 5858113 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.4844. Min Act: -0.1700
Data Index: 8788260 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.4219. Min Act: -0.1700
Data Index: 3752256 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.4531. Min Act: -0.1700
Data Index: 7007047 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.4531. Min Act: -0.1700
Data Index: 4705552 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.4219. Min Act: -0.1700
Data Index: 1840483 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.4219. Min Act: -0.1700
Data Index: 6071459 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.3906. Min Act: -0.1700
Data Index: 5509572 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.3906. Min Act: -0.1700
Data Index: 3525911 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7969. Min Range: -5.7969
Max Act: 5.3906. Min Act: -0.1700
Data Index: 1111199 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19