Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.5582. Min Act: -0.1700
Data Index: 2144833 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.5269. Min Act: -0.1700
Data Index: 4925954 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4957. Min Act: -0.1700
Data Index: 4806398 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4957. Min Act: -0.1700
Data Index: 2945991 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4644. Min Act: -0.1700
Data Index: 4606183 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4644. Min Act: -0.1700
Data Index: 1015196 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4332. Min Act: -0.1700
Data Index: 8545371 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4644. Min Act: -0.1700
Data Index: 3860033 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4019. Min Act: -0.1700
Data Index: 7314853 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4332. Min Act: -0.1700
Data Index: 5594433 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.3707. Min Act: -0.1700
Data Index: 1418338 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4019. Min Act: -0.1700
Data Index: 4603635 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4019. Min Act: -0.1700
Data Index: 1549090 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4019. Min Act: -0.1700
Data Index: 6789028 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4019. Min Act: -0.1700
Data Index: 7932713 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4019. Min Act: -0.1700
Data Index: 5418995 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.3707. Min Act: -0.1700
Data Index: 6208343 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4019. Min Act: -0.1700
Data Index: 6413314 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.4019. Min Act: -0.1700
Data Index: 4554903 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5582. Min Range: -4.5582
Max Act: 4.3394. Min Act: -0.1700
Data Index: 5856986 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19