Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2396 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.3216. Min Act: -0.1700
Data Index: 595424 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.2903. Min Act: -0.1700
Data Index: 4385374 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.2903. Min Act: -0.1700
Data Index: 3998937 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.2745. Min Act: -0.1700
Data Index: 2353485 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1488. Min Act: -0.1700
Data Index: 6988146 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1645. Min Act: -0.1700
Data Index: 1821419 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1330. Min Act: -0.1700
Data Index: 1603057 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1173. Min Act: -0.1700
Data Index: 5175447 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1330. Min Act: -0.1700
Data Index: 1603020 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1330. Min Act: -0.1700
Data Index: 3556055 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1173. Min Act: -0.1700
Data Index: 183185 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1173. Min Act: -0.1700
Data Index: 6112692 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1173. Min Act: -0.1700
Data Index: 4144698 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1015. Min Act: -0.1700
Data Index: 7878919 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.0857. Min Act: -0.1700
Data Index: 1465581 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.0700. Min Act: -0.1700
Data Index: 5568846 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.0700. Min Act: -0.1700
Data Index: 3125833 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.0857. Min Act: -0.1700
Data Index: 501650 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.1015. Min Act: -0.1700
Data Index: 7804319 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3216. Min Range: -3.3216
Max Act: 3.0700. Min Act: -0.1700
Data Index: 7056612 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19