Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3977 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0145. Min Range: -6.0145
Max Act: 6.0145. Min Act: -0.1700
Data Index: 1212800 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.9207. Min Act: -0.1700
Data Index: 3422149 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.8895. Min Act: -0.1700
Data Index: 2566215 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.8270. Min Act: -0.1700
Data Index: 1212798 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7957. Min Act: -0.1700
Data Index: 1700819 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7957. Min Act: -0.1700
Data Index: 3160717 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7957. Min Act: -0.1700
Data Index: 4099052 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7957. Min Act: -0.1700
Data Index: 2996400 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7645. Min Act: -0.1700
Data Index: 7716686 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7645. Min Act: -0.1700
Data Index: 3258581 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7645. Min Act: -0.1700
Data Index: 2395020 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7645. Min Act: -0.1700
Data Index: 4369936 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7645. Min Act: -0.1700
Data Index: 8460119 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7645. Min Act: -0.1700
Data Index: 1827737 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7332. Min Act: -0.1700
Data Index: 4952076 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7332. Min Act: -0.1700
Data Index: 3824187 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7332. Min Act: -0.1700
Data Index: 7361237 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7332. Min Act: -0.1700
Data Index: 7669156 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7332. Min Act: -0.1700
Data Index: 650436 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0145. Min Range: -6.0145
Max Act: 5.7332. Min Act: -0.1700
Data Index: 1212799 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19