Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 617 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.5743. Min Act: -0.1700
Data Index: 7960490 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.4805. Min Act: -0.1700
Data Index: 5758462 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.4180. Min Act: -0.1700
Data Index: 6289723 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.3868. Min Act: -0.1700
Data Index: 8762000 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.3555. Min Act: -0.1700
Data Index: 1864245 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.4180. Min Act: -0.1700
Data Index: 6749799 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.2930. Min Act: -0.1700
Data Index: 3395672 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.3555. Min Act: -0.1700
Data Index: 1062057 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.3555. Min Act: -0.1700
Data Index: 7781556 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.3243. Min Act: -0.1700
Data Index: 5652399 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.3243. Min Act: -0.1700
Data Index: 2239229 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.3555. Min Act: -0.1700
Data Index: 7165902 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.3555. Min Act: -0.1700
Data Index: 6372854 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.2618. Min Act: -0.1700
Data Index: 6271104 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.2930. Min Act: -0.1700
Data Index: 5304717 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.3243. Min Act: -0.1700
Data Index: 397073 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.3243. Min Act: -0.1700
Data Index: 1396313 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.2618. Min Act: -0.1700
Data Index: 6995927 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.2618. Min Act: -0.1700
Data Index: 540056 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5743. Min Range: -5.5743
Max Act: 5.2618. Min Act: -0.1700
Data Index: 535168 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19