Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3727 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1199. Min Range: -7.1199
Max Act: 7.1199. Min Act: -0.1700
Data Index: 2384244 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.6824. Min Act: -0.1700
Data Index: 2308248 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.5886. Min Act: -0.1700
Data Index: 2118095 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.4636. Min Act: -0.1700
Data Index: 5418332 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.3074. Min Act: -0.1700
Data Index: 3475752 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.3074. Min Act: -0.1700
Data Index: 231542 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.2761. Min Act: -0.1700
Data Index: 6291207 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.2136. Min Act: -0.1700
Data Index: 5649299 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.1824. Min Act: -0.1700
Data Index: 1340426 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.1824. Min Act: -0.1700
Data Index: 7320138 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.1824. Min Act: -0.1700
Data Index: 4995685 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.1199. Min Act: -0.1700
Data Index: 7872486 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.0886. Min Act: -0.1700
Data Index: 2162868 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.0261. Min Act: -0.1700
Data Index: 3128996 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.0261. Min Act: -0.1700
Data Index: 1842287 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.0261. Min Act: -0.1700
Data Index: 2303118 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.0261. Min Act: -0.1700
Data Index: 5024956 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.0261. Min Act: -0.1700
Data Index: 3633142 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.0261. Min Act: -0.1700
Data Index: 4123665 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1199. Min Range: -7.1199
Max Act: 6.0261. Min Act: -0.1700
Data Index: 2801916 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19