Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.6521. Min Act: -0.1700
Data Index: 8526917 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.4021. Min Act: -0.1700
Data Index: 6609546 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.4021. Min Act: -0.1700
Data Index: 1257198 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.3708. Min Act: -0.1700
Data Index: 3191032 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.3708. Min Act: -0.1700
Data Index: 2813705 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.1833. Min Act: -0.1700
Data Index: 8744218 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.1833. Min Act: -0.1700
Data Index: 3617776 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.1833. Min Act: -0.1700
Data Index: 2929322 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.1521. Min Act: -0.1700
Data Index: 4762559 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.0271. Min Act: -0.1700
Data Index: 2567954 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6521. Min Range: -7.6521
Max Act: 6.9958. Min Act: -0.1700
Data Index: 4334841 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6521. Min Range: -7.6521
Max Act: 6.9958. Min Act: -0.1700
Data Index: 504406 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6521. Min Range: -7.6521
Max Act: 6.9958. Min Act: -0.1700
Data Index: 6983781 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6521. Min Range: -7.6521
Max Act: 7.0271. Min Act: -0.1700
Data Index: 5257443 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6521. Min Range: -7.6521
Max Act: 6.9646. Min Act: -0.1700
Data Index: 146310 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6521. Min Range: -7.6521
Max Act: 6.9646. Min Act: -0.1700
Data Index: 2990360 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6521. Min Range: -7.6521
Max Act: 6.9646. Min Act: -0.1700
Data Index: 6305509 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6521. Min Range: -7.6521
Max Act: 6.9958. Min Act: -0.1700
Data Index: 5005140 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6521. Min Range: -7.6521
Max Act: 6.9333. Min Act: -0.1700
Data Index: 3678792 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6521. Min Range: -7.6521
Max Act: 6.9333. Min Act: -0.1700
Data Index: 174925 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19