Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6371 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.9497. Min Act: -0.1700
Data Index: 8319283 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.9185. Min Act: -0.1700
Data Index: 2873648 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.8872. Min Act: -0.1700
Data Index: 5719871 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.8247. Min Act: -0.1700
Data Index: 3292583 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.7622. Min Act: -0.1700
Data Index: 8541238 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.7310. Min Act: -0.1700
Data Index: 582493 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.7622. Min Act: -0.1700
Data Index: 6588886 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.7622. Min Act: -0.1700
Data Index: 1376402 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6685. Min Act: -0.1700
Data Index: 1066997 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6685. Min Act: -0.1700
Data Index: 2399060 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6685. Min Act: -0.1700
Data Index: 5426255 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6372. Min Act: -0.1700
Data Index: 127395 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6372. Min Act: -0.1700
Data Index: 5547963 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6060. Min Act: -0.1700
Data Index: 6733576 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6060. Min Act: -0.1700
Data Index: 8491748 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6060. Min Act: -0.1700
Data Index: 6139874 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6060. Min Act: -0.1700
Data Index: 611787 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.5747. Min Act: -0.1700
Data Index: 2386425 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6060. Min Act: -0.1700
Data Index: 1431499 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.5435. Min Act: -0.1700
Data Index: 3568680 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19