Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4519 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.7924. Min Act: -0.1700
Data Index: 1377229 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.7612. Min Act: -0.1700
Data Index: 3047484 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.7612. Min Act: -0.1700
Data Index: 3067019 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.7612. Min Act: -0.1700
Data Index: 7211453 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.7299. Min Act: -0.1700
Data Index: 7000364 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6987. Min Act: -0.1700
Data Index: 4476070 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6674. Min Act: -0.1700
Data Index: 8454466 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6362. Min Act: -0.1700
Data Index: 5292960 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6049. Min Act: -0.1700
Data Index: 7160925 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6049. Min Act: -0.1700
Data Index: 3327562 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6362. Min Act: -0.1700
Data Index: 2834503 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6362. Min Act: -0.1700
Data Index: 1812532 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6362. Min Act: -0.1700
Data Index: 549 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6362. Min Act: -0.1700
Data Index: 3067016 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6362. Min Act: -0.1700
Data Index: 2161530 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.5737. Min Act: -0.1700
Data Index: 4816794 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.5737. Min Act: -0.1700
Data Index: 7160923 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6049. Min Act: -0.1700
Data Index: 8582362 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.5737. Min Act: -0.1700
Data Index: 7076836 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7924. Min Range: -5.7924
Max Act: 5.6049. Min Act: -0.1700
Data Index: 5711976 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19