Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 413 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.6373. Min Act: -0.1700
Data Index: 8129475 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.5435. Min Act: -0.1700
Data Index: 2022237 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.6060. Min Act: -0.1700
Data Index: 4979604 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.4810. Min Act: -0.1700
Data Index: 8573594 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.4810. Min Act: -0.1700
Data Index: 6228457 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.3560. Min Act: -0.1700
Data Index: 1383037 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.3560. Min Act: -0.1700
Data Index: 1910654 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.2935. Min Act: -0.1700
Data Index: 7673388 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.3248. Min Act: -0.1700
Data Index: 4593898 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.3560. Min Act: -0.1700
Data Index: 1774638 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.2935. Min Act: -0.1700
Data Index: 2380774 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.2310. Min Act: -0.1700
Data Index: 1774639 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.1998. Min Act: -0.1700
Data Index: 4879025 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.1373. Min Act: -0.1700
Data Index: 550269 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.1060. Min Act: -0.1700
Data Index: 4275790 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.0435. Min Act: -0.1700
Data Index: 5942269 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.0435. Min Act: -0.1700
Data Index: 5306249 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.0123. Min Act: -0.1700
Data Index: 7723482 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6373. Min Range: -5.6373
Max Act: 5.0123. Min Act: -0.1700
Data Index: 4896902 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6373. Min Range: -5.6373
Max Act: 4.9498. Min Act: -0.1700
Data Index: 2810159 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19