Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.9310. Min Act: -0.1700
Data Index: 5352477 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.7435. Min Act: -0.1700
Data Index: 5413814 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.6810. Min Act: -0.1700
Data Index: 5687262 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.6810. Min Act: -0.1700
Data Index: 1406841 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.6185. Min Act: -0.1700
Data Index: 7216251 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.6185. Min Act: -0.1700
Data Index: 6784364 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.6185. Min Act: -0.1700
Data Index: 5662819 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.5560. Min Act: -0.1700
Data Index: 4989110 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.5560. Min Act: -0.1700
Data Index: 904532 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.4310. Min Act: -0.1700
Data Index: 8595942 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.4935. Min Act: -0.1700
Data Index: 7416513 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.4935. Min Act: -0.1700
Data Index: 1461852 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.5560. Min Act: -0.1700
Data Index: 2129549 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.4935. Min Act: -0.1700
Data Index: 2174184 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.4935. Min Act: -0.1700
Data Index: 1026022 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.4310. Min Act: -0.1700
Data Index: 1097005 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.4310. Min Act: -0.1700
Data Index: 3181891 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.4310. Min Act: -0.1700
Data Index: 8583820 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.4310. Min Act: -0.1700
Data Index: 7682439 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9310. Min Range: -12.9310
Max Act: 12.3685. Min Act: -0.1700
Data Index: 6844385 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19