Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3796 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.8381. Min Act: -0.1700
Data Index: 4849439 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.8381. Min Act: -0.1700
Data Index: 902385 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.7756. Min Act: -0.1700
Data Index: 1230336 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.7756. Min Act: -0.1700
Data Index: 93062 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.7443. Min Act: -0.1700
Data Index: 6142866 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.7130. Min Act: -0.1700
Data Index: 940367 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6817. Min Act: -0.1700
Data Index: 1590780 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6817. Min Act: -0.1700
Data Index: 8069407 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6817. Min Act: -0.1700
Data Index: 510004 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6504. Min Act: -0.1700
Data Index: 788157 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6504. Min Act: -0.1700
Data Index: 5261355 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6504. Min Act: -0.1700
Data Index: 5560853 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6504. Min Act: -0.1700
Data Index: 165605 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6504. Min Act: -0.1700
Data Index: 7637651 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6191. Min Act: -0.1700
Data Index: 5826750 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6191. Min Act: -0.1700
Data Index: 1297059 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6191. Min Act: -0.1700
Data Index: 4238169 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.5878. Min Act: -0.1700
Data Index: 5869114 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.6191. Min Act: -0.1700
Data Index: 5500884 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8381. Min Range: -3.8381
Max Act: 3.5878. Min Act: -0.1700
Data Index: 844121 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19