Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4607 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.6830. Min Act: -0.1700
Data Index: 4167563 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.6517. Min Act: -0.1700
Data Index: 7493628 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.6205. Min Act: -0.1700
Data Index: 7061291 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.6205. Min Act: -0.1700
Data Index: 455598 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.5892. Min Act: -0.1700
Data Index: 6109857 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.5580. Min Act: -0.1700
Data Index: 7401882 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.5267. Min Act: -0.1700
Data Index: 1264150 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.4955. Min Act: -0.1700
Data Index: 247271 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.4955. Min Act: -0.1700
Data Index: 7458045 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.4955. Min Act: -0.1700
Data Index: 823514 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.4642. Min Act: -0.1700
Data Index: 2635605 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.4642. Min Act: -0.1700
Data Index: 863013 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.4017. Min Act: -0.1700
Data Index: 3862801 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.3705. Min Act: -0.1700
Data Index: 4167560 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.3705. Min Act: -0.1700
Data Index: 5416213 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.3705. Min Act: -0.1700
Data Index: 8666110 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.3392. Min Act: -0.1700
Data Index: 8668416 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.2455. Min Act: -0.1700
Data Index: 8823594 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.2455. Min Act: -0.1700
Data Index: 6379852 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6830. Min Range: -5.6830
Max Act: 5.2142. Min Act: -0.1700
Data Index: 3485880 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19