Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6315. Min Range: -7.6315
Max Act: 7.6315. Min Act: -0.1700
Data Index: 4394688 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6315. Min Range: -7.6315
Max Act: 7.5065. Min Act: -0.1700
Data Index: 6106930 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6315. Min Range: -7.6315
Max Act: 7.1315. Min Act: -0.1700
Data Index: 973492 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6315. Min Range: -7.6315
Max Act: 7.0065. Min Act: -0.1700
Data Index: 5987520 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6315. Min Range: -7.6315
Max Act: 7.0065. Min Act: -0.1700
Data Index: 1374318 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6315. Min Range: -7.6315
Max Act: 7.0065. Min Act: -0.1700
Data Index: 3321304 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6315. Min Range: -7.6315
Max Act: 7.0065. Min Act: -0.1700
Data Index: 6747974 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.9753. Min Act: -0.1700
Data Index: 4189809 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6315. Min Range: -7.6315
Max Act: 7.0065. Min Act: -0.1700
Data Index: 3318411 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.9440. Min Act: -0.1700
Data Index: 2552251 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.9128. Min Act: -0.1700
Data Index: 3823748 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.9440. Min Act: -0.1700
Data Index: 6615336 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.8815. Min Act: -0.1700
Data Index: 3027452 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.8815. Min Act: -0.1700
Data Index: 2227904 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.8815. Min Act: -0.1700
Data Index: 167167 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.8190. Min Act: -0.1700
Data Index: 3243615 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.8190. Min Act: -0.1700
Data Index: 5736109 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.8503. Min Act: -0.1700
Data Index: 4216980 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.8503. Min Act: -0.1700
Data Index: 1289703 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6315. Min Range: -7.6315
Max Act: 6.8190. Min Act: -0.1700
Data Index: 8030629 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19