Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5139 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8301. Min Range: -8.8301
Max Act: 8.8301. Min Act: -0.1700
Data Index: 5826693 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8301. Min Range: -8.8301
Max Act: 8.4551. Min Act: -0.1700
Data Index: 5724081 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8301. Min Range: -8.8301
Max Act: 8.2051. Min Act: -0.1700
Data Index: 3602694 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8301. Min Range: -8.8301
Max Act: 8.1114. Min Act: -0.1700
Data Index: 645938 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8301. Min Range: -8.8301
Max Act: 8.1114. Min Act: -0.1700
Data Index: 3933792 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8301. Min Range: -8.8301
Max Act: 8.0489. Min Act: -0.1700
Data Index: 2983149 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.9239. Min Act: -0.1700
Data Index: 3246407 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.8301. Min Act: -0.1700
Data Index: 5944753 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.7364. Min Act: -0.1700
Data Index: 5195508 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.7676. Min Act: -0.1700
Data Index: 7957447 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.7364. Min Act: -0.1700
Data Index: 2950528 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.7364. Min Act: -0.1700
Data Index: 4013257 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.7051. Min Act: -0.1700
Data Index: 8326422 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.7051. Min Act: -0.1700
Data Index: 7123470 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.7051. Min Act: -0.1700
Data Index: 539818 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.6739. Min Act: -0.1700
Data Index: 2025630 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.6426. Min Act: -0.1700
Data Index: 8187583 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.6114. Min Act: -0.1700
Data Index: 1121188 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.6114. Min Act: -0.1700
Data Index: 640536 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8301. Min Range: -8.8301
Max Act: 7.5801. Min Act: -0.1700
Data Index: 3863543 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19