Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2864 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.6153. Min Act: -0.1700
Data Index: 7819094 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.5528. Min Act: -0.1700
Data Index: 1602819 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.4903. Min Act: -0.1700
Data Index: 207780 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.4903. Min Act: -0.1700
Data Index: 3626169 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.4903. Min Act: -0.1700
Data Index: 6224819 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.4278. Min Act: -0.1700
Data Index: 6424539 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.3653. Min Act: -0.1700
Data Index: 7195015 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.3653. Min Act: -0.1700
Data Index: 7945702 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.3028. Min Act: -0.1700
Data Index: 4251127 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.3028. Min Act: -0.1700
Data Index: 3800613 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.2403. Min Act: -0.1700
Data Index: 8180106 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.2403. Min Act: -0.1700
Data Index: 8697731 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.2403. Min Act: -0.1700
Data Index: 3114709 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.2403. Min Act: -0.1700
Data Index: 7033704 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.2403. Min Act: -0.1700
Data Index: 4953367 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.1778. Min Act: -0.1700
Data Index: 3779170 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.1778. Min Act: -0.1700
Data Index: 6857288 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.1778. Min Act: -0.1700
Data Index: 2603565 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.1778. Min Act: -0.1700
Data Index: 6517706 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6153. Min Range: -10.6153
Max Act: 10.1153. Min Act: -0.1700
Data Index: 3902622 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19