Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4402 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.7427. Min Act: -0.1700
Data Index: 4207135 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.4302. Min Act: -0.1700
Data Index: 5686106 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.3052. Min Act: -0.1700
Data Index: 5474796 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.2740. Min Act: -0.1700
Data Index: 1056465 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.2740. Min Act: -0.1700
Data Index: 2413564 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.2427. Min Act: -0.1700
Data Index: 5888720 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.2427. Min Act: -0.1700
Data Index: 4988603 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.1177. Min Act: -0.1700
Data Index: 6304081 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.1177. Min Act: -0.1700
Data Index: 3853109 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.1177. Min Act: -0.1700
Data Index: 1056464 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.0865. Min Act: -0.1700
Data Index: 6601008 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.0552. Min Act: -0.1700
Data Index: 2484651 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.0552. Min Act: -0.1700
Data Index: 2939883 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7427. Min Range: -6.7427
Max Act: 6.0240. Min Act: -0.1700
Data Index: 640607 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7427. Min Range: -6.7427
Max Act: 5.9927. Min Act: -0.1700
Data Index: 6289879 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7427. Min Range: -6.7427
Max Act: 5.9927. Min Act: -0.1700
Data Index: 3618668 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7427. Min Range: -6.7427
Max Act: 5.9927. Min Act: -0.1700
Data Index: 7527099 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7427. Min Range: -6.7427
Max Act: 5.9615. Min Act: -0.1700
Data Index: 922054 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7427. Min Range: -6.7427
Max Act: 5.9927. Min Act: -0.1700
Data Index: 702089 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7427. Min Range: -6.7427
Max Act: 5.9615. Min Act: -0.1700
Data Index: 3802961 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19