Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3157 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.6097. Min Act: -0.1700
Data Index: 7987467 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.6097. Min Act: -0.1700
Data Index: 710907 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.6097. Min Act: -0.1700
Data Index: 8595365 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.6097. Min Act: -0.1700
Data Index: 6723120 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.6722. Min Act: -0.1700
Data Index: 11634 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.4222. Min Act: -0.1700
Data Index: 7877627 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.4222. Min Act: -0.1700
Data Index: 4751783 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.4222. Min Act: -0.1700
Data Index: 6741788 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.4222. Min Act: -0.1700
Data Index: 4205635 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.3597. Min Act: -0.1700
Data Index: 4341414 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.3597. Min Act: -0.1700
Data Index: 8630668 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.2972. Min Act: -0.1700
Data Index: 7013109 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.2972. Min Act: -0.1700
Data Index: 6961113 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.2972. Min Act: -0.1700
Data Index: 6853714 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.2972. Min Act: -0.1700
Data Index: 4228876 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.2347. Min Act: -0.1700
Data Index: 7399310 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.2347. Min Act: -0.1700
Data Index: 4913572 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.1722. Min Act: -0.1700
Data Index: 5164923 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.2347. Min Act: -0.1700
Data Index: 2404393 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6722. Min Range: -12.6722
Max Act: 12.2347. Min Act: -0.1700
Data Index: 1471279 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19