Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 658 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.9519. Min Act: -0.1700
Data Index: 5083425 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.8582. Min Act: -0.1700
Data Index: 3922896 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.7644. Min Act: -0.1700
Data Index: 4786335 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.6082. Min Act: -0.1700
Data Index: 992615 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.6082. Min Act: -0.1700
Data Index: 4172743 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.6082. Min Act: -0.1700
Data Index: 7459367 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.6394. Min Act: -0.1700
Data Index: 1677131 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.5769. Min Act: -0.1700
Data Index: 4405507 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.5457. Min Act: -0.1700
Data Index: 1948963 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.4832. Min Act: -0.1700
Data Index: 5383817 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.4832. Min Act: -0.1700
Data Index: 4382392 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.4832. Min Act: -0.1700
Data Index: 3617207 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.4519. Min Act: -0.1700
Data Index: 1810662 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.4519. Min Act: -0.1700
Data Index: 5879968 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.4207. Min Act: -0.1700
Data Index: 5821681 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.4207. Min Act: -0.1700
Data Index: 6637469 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.4207. Min Act: -0.1700
Data Index: 6589109 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.4519. Min Act: -0.1700
Data Index: 6158547 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.3894. Min Act: -0.1700
Data Index: 5636685 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9519. Min Range: -5.9519
Max Act: 5.3894. Min Act: -0.1700
Data Index: 2790316 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19