Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4933 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.1709. Min Act: -0.1700
Data Index: 7268421 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.1397. Min Act: -0.1700
Data Index: 5912428 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.1084. Min Act: -0.1700
Data Index: 6648272 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.0459. Min Act: -0.1700
Data Index: 982527 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.0147. Min Act: -0.1700
Data Index: 143948 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9834. Min Act: -0.1700
Data Index: 414112 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 4282290 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 6159933 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 7242881 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8897. Min Act: -0.1700
Data Index: 112101 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8897. Min Act: -0.1700
Data Index: 8180763 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 7466372 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8584. Min Act: -0.1700
Data Index: 8686848 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8584. Min Act: -0.1700
Data Index: 7424015 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8584. Min Act: -0.1700
Data Index: 756464 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8272. Min Act: -0.1700
Data Index: 8541535 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8272. Min Act: -0.1700
Data Index: 2942327 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8272. Min Act: -0.1700
Data Index: 7307322 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.7959. Min Act: -0.1700
Data Index: 8426104 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.7647. Min Act: -0.1700
Data Index: 6106491 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19