Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5944 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3302. Min Range: -8.3302
Max Act: 8.3302. Min Act: -0.1700
Data Index: 1180354 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3302. Min Range: -8.3302
Max Act: 8.2677. Min Act: -0.1700
Data Index: 7571732 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3302. Min Range: -8.3302
Max Act: 8.1740. Min Act: -0.1700
Data Index: 5405074 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3302. Min Range: -8.3302
Max Act: 8.0177. Min Act: -0.1700
Data Index: 1089135 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3302. Min Range: -8.3302
Max Act: 8.0177. Min Act: -0.1700
Data Index: 8357986 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3302. Min Range: -8.3302
Max Act: 8.0490. Min Act: -0.1700
Data Index: 7610204 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3302. Min Range: -8.3302
Max Act: 8.0177. Min Act: -0.1700
Data Index: 5523390 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3302. Min Range: -8.3302
Max Act: 8.0490. Min Act: -0.1700
Data Index: 4350879 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.9865. Min Act: -0.1700
Data Index: 8212877 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.8927. Min Act: -0.1700
Data Index: 717738 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.8615. Min Act: -0.1700
Data Index: 4950351 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.8615. Min Act: -0.1700
Data Index: 3291938 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.8615. Min Act: -0.1700
Data Index: 3165093 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.7990. Min Act: -0.1700
Data Index: 475455 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.7990. Min Act: -0.1700
Data Index: 6732794 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.7677. Min Act: -0.1700
Data Index: 1752849 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.7052. Min Act: -0.1700
Data Index: 2312146 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.7052. Min Act: -0.1700
Data Index: 7393541 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.6740. Min Act: -0.1700
Data Index: 6898403 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3302. Min Range: -8.3302
Max Act: 7.6740. Min Act: -0.1700
Data Index: 4316071 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19