Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.6981. Min Act: -0.1700
Data Index: 5994503 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.6043. Min Act: -0.1700
Data Index: 2311488 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.5731. Min Act: -0.1700
Data Index: 8728235 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.4481. Min Act: -0.1700
Data Index: 2812773 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.4168. Min Act: -0.1700
Data Index: 1516071 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.3856. Min Act: -0.1700
Data Index: 8093241 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.3543. Min Act: -0.1700
Data Index: 1794758 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.3856. Min Act: -0.1700
Data Index: 2732932 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.3543. Min Act: -0.1700
Data Index: 3725679 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.3231. Min Act: -0.1700
Data Index: 6632705 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.2918. Min Act: -0.1700
Data Index: 6937505 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.2918. Min Act: -0.1700
Data Index: 5763415 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.2918. Min Act: -0.1700
Data Index: 8416036 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.2918. Min Act: -0.1700
Data Index: 8360020 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.3231. Min Act: -0.1700
Data Index: 431462 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.2918. Min Act: -0.1700
Data Index: 8767942 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.2606. Min Act: -0.1700
Data Index: 5248326 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.2606. Min Act: -0.1700
Data Index: 1659387 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.2606. Min Act: -0.1700
Data Index: 1372522 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6981. Min Range: -5.6981
Max Act: 5.1981. Min Act: -0.1700
Data Index: 6558089 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19