Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.5793. Min Act: -0.1700
Data Index: 6483877 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.2356. Min Act: -0.1700
Data Index: 551510 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.2043. Min Act: -0.1700
Data Index: 4772921 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.2043. Min Act: -0.1700
Data Index: 6258025 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.1731. Min Act: -0.1700
Data Index: 5629328 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.1731. Min Act: -0.1700
Data Index: 2153415 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.1731. Min Act: -0.1700
Data Index: 1703984 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.1418. Min Act: -0.1700
Data Index: 3319024 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.1418. Min Act: -0.1700
Data Index: 586697 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.1418. Min Act: -0.1700
Data Index: 110626 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.1106. Min Act: -0.1700
Data Index: 1188355 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.1106. Min Act: -0.1700
Data Index: 8712852 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.0793. Min Act: -0.1700
Data Index: 8004431 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.1106. Min Act: -0.1700
Data Index: 7176880 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.0481. Min Act: -0.1700
Data Index: 5913025 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.0168. Min Act: -0.1700
Data Index: 2756072 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.0168. Min Act: -0.1700
Data Index: 4685658 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.0168. Min Act: -0.1700
Data Index: 7441418 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5793. Min Range: -5.5793
Max Act: 5.0481. Min Act: -0.1700
Data Index: 7326116 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5793. Min Range: -5.5793
Max Act: 4.9543. Min Act: -0.1700
Data Index: 6822675 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19