Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1661 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.7981. Min Act: -0.1700
Data Index: 6601110 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.6106. Min Act: -0.1700
Data Index: 2258046 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.5481. Min Act: -0.1700
Data Index: 5338846 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.5481. Min Act: -0.1700
Data Index: 1970438 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.5169. Min Act: -0.1700
Data Index: 3212974 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.4856. Min Act: -0.1700
Data Index: 2678170 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.3919. Min Act: -0.1700
Data Index: 3735852 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.3919. Min Act: -0.1700
Data Index: 6737981 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.3606. Min Act: -0.1700
Data Index: 1286488 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.3606. Min Act: -0.1700
Data Index: 3040855 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.3294. Min Act: -0.1700
Data Index: 4935514 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.3294. Min Act: -0.1700
Data Index: 381097 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.2669. Min Act: -0.1700
Data Index: 2100227 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.2669. Min Act: -0.1700
Data Index: 8208224 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.2669. Min Act: -0.1700
Data Index: 2213342 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.2356. Min Act: -0.1700
Data Index: 2283601 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.2356. Min Act: -0.1700
Data Index: 6912153 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.2356. Min Act: -0.1700
Data Index: 2567262 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.2044. Min Act: -0.1700
Data Index: 613259 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7981. Min Range: -5.7981
Max Act: 5.2044. Min Act: -0.1700
Data Index: 2732709 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19