Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1268 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.7198. Min Act: -0.1700
Data Index: 2839573 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.6886. Min Act: -0.1700
Data Index: 1382714 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5948. Min Act: -0.1700
Data Index: 6837354 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5636. Min Act: -0.1700
Data Index: 1195115 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5636. Min Act: -0.1700
Data Index: 7194396 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5323. Min Act: -0.1700
Data Index: 5352525 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5011. Min Act: -0.1700
Data Index: 5830078 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5011. Min Act: -0.1700
Data Index: 2893669 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.5011. Min Act: -0.1700
Data Index: 4411403 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4698. Min Act: -0.1700
Data Index: 252107 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4698. Min Act: -0.1700
Data Index: 6760228 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4698. Min Act: -0.1700
Data Index: 3311016 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4386. Min Act: -0.1700
Data Index: 3337232 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4386. Min Act: -0.1700
Data Index: 2406406 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4386. Min Act: -0.1700
Data Index: 2516583 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4386. Min Act: -0.1700
Data Index: 1499701 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4386. Min Act: -0.1700
Data Index: 4223449 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4386. Min Act: -0.1700
Data Index: 4519865 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4386. Min Act: -0.1700
Data Index: 1426987 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4073. Min Act: -0.1700
Data Index: 4639929 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19