Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 65 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5347. Min Range: -7.5347
Max Act: 7.5347. Min Act: -0.1700
Data Index: 705549 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5347. Min Range: -7.5347
Max Act: 7.2534. Min Act: -0.1700
Data Index: 2128192 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5347. Min Range: -7.5347
Max Act: 7.1909. Min Act: -0.1700
Data Index: 2677903 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5347. Min Range: -7.5347
Max Act: 7.1597. Min Act: -0.1700
Data Index: 32627 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5347. Min Range: -7.5347
Max Act: 7.0972. Min Act: -0.1700
Data Index: 2638809 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5347. Min Range: -7.5347
Max Act: 7.1284. Min Act: -0.1700
Data Index: 3264463 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5347. Min Range: -7.5347
Max Act: 7.0347. Min Act: -0.1700
Data Index: 8435235 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5347. Min Range: -7.5347
Max Act: 7.0034. Min Act: -0.1700
Data Index: 6858395 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5347. Min Range: -7.5347
Max Act: 7.0034. Min Act: -0.1700
Data Index: 2857639 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.9722. Min Act: -0.1700
Data Index: 351059 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.9409. Min Act: -0.1700
Data Index: 4828670 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.9409. Min Act: -0.1700
Data Index: 704198 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.9409. Min Act: -0.1700
Data Index: 8103737 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.9409. Min Act: -0.1700
Data Index: 2314803 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.9097. Min Act: -0.1700
Data Index: 8258163 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.9097. Min Act: -0.1700
Data Index: 2890535 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.8784. Min Act: -0.1700
Data Index: 5971727 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.9097. Min Act: -0.1700
Data Index: 3041116 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.9097. Min Act: -0.1700
Data Index: 3301921 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5347. Min Range: -7.5347
Max Act: 6.9097. Min Act: -0.1700
Data Index: 2660080 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19