Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5912 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3897. Min Range: -7.3897
Max Act: 7.3897. Min Act: -0.1700
Data Index: 6316570 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3897. Min Range: -7.3897
Max Act: 7.2647. Min Act: -0.1700
Data Index: 3316834 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3897. Min Range: -7.3897
Max Act: 7.2647. Min Act: -0.1700
Data Index: 569730 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3897. Min Range: -7.3897
Max Act: 7.1084. Min Act: -0.1700
Data Index: 40865 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3897. Min Range: -7.3897
Max Act: 7.0459. Min Act: -0.1700
Data Index: 4863763 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3897. Min Range: -7.3897
Max Act: 7.0147. Min Act: -0.1700
Data Index: 8572641 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3897. Min Range: -7.3897
Max Act: 7.0147. Min Act: -0.1700
Data Index: 6455113 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.9834. Min Act: -0.1700
Data Index: 968844 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.9834. Min Act: -0.1700
Data Index: 6332200 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.9522. Min Act: -0.1700
Data Index: 6153891 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.9522. Min Act: -0.1700
Data Index: 1307485 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.9209. Min Act: -0.1700
Data Index: 6324082 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.9209. Min Act: -0.1700
Data Index: 1880107 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.8897. Min Act: -0.1700
Data Index: 2626155 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.8897. Min Act: -0.1700
Data Index: 5678480 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.7959. Min Act: -0.1700
Data Index: 3729805 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.8272. Min Act: -0.1700
Data Index: 3294729 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.7959. Min Act: -0.1700
Data Index: 6741545 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.7959. Min Act: -0.1700
Data Index: 4197246 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3897. Min Range: -7.3897
Max Act: 6.7647. Min Act: -0.1700
Data Index: 6439797 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19