Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5920 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.2291. Min Act: -0.1700
Data Index: 763491 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0103. Min Act: -0.1700
Data Index: 2523604 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.8228. Min Act: -0.1700
Data Index: 4969857 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.7916. Min Act: -0.1700
Data Index: 416050 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.7916. Min Act: -0.1700
Data Index: 2102753 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.7916. Min Act: -0.1700
Data Index: 2405217 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.7291. Min Act: -0.1700
Data Index: 2191055 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.7291. Min Act: -0.1700
Data Index: 1915161 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.7291. Min Act: -0.1700
Data Index: 3782534 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.7291. Min Act: -0.1700
Data Index: 3155785 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.6978. Min Act: -0.1700
Data Index: 1312610 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.6666. Min Act: -0.1700
Data Index: 7712776 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.6978. Min Act: -0.1700
Data Index: 8057842 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.6978. Min Act: -0.1700
Data Index: 6381224 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.6666. Min Act: -0.1700
Data Index: 3867975 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.6666. Min Act: -0.1700
Data Index: 7947758 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.6666. Min Act: -0.1700
Data Index: 3291792 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.6353. Min Act: -0.1700
Data Index: 6788866 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.6353. Min Act: -0.1700
Data Index: 4275047 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.6041. Min Act: -0.1700
Data Index: 3404991 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19