Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.3165. Min Act: -0.1700
Data Index: 6501373 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.2540. Min Act: -0.1700
Data Index: 673446 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.2540. Min Act: -0.1700
Data Index: 5772073 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.2540. Min Act: -0.1700
Data Index: 6501372 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.1915. Min Act: -0.1700
Data Index: 8664418 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.1915. Min Act: -0.1700
Data Index: 4965720 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.2227. Min Act: -0.1700
Data Index: 1591113 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.1602. Min Act: -0.1700
Data Index: 7574211 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.1290. Min Act: -0.1700
Data Index: 856956 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.1290. Min Act: -0.1700
Data Index: 4456836 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0977. Min Act: -0.1700
Data Index: 4344122 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0977. Min Act: -0.1700
Data Index: 7011129 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0977. Min Act: -0.1700
Data Index: 673448 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0665. Min Act: -0.1700
Data Index: 5456325 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0665. Min Act: -0.1700
Data Index: 1733716 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0665. Min Act: -0.1700
Data Index: 1320511 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0665. Min Act: -0.1700
Data Index: 6188843 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0352. Min Act: -0.1700
Data Index: 3582120 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0040. Min Act: -0.1700
Data Index: 1077361 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0352. Min Act: -0.1700
Data Index: 2848681 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19