Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7231. Min Range: -5.7231
Max Act: 5.7231. Min Act: -0.1700
Data Index: 6153138 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7231. Min Range: -5.7231
Max Act: 5.2543. Min Act: -0.1700
Data Index: 5618380 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7231. Min Range: -5.7231
Max Act: 5.2231. Min Act: -0.1700
Data Index: 191722 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7231. Min Range: -5.7231
Max Act: 5.1606. Min Act: -0.1700
Data Index: 4602657 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7231. Min Range: -5.7231
Max Act: 5.0981. Min Act: -0.1700
Data Index: 919933 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.9731. Min Act: -0.1700
Data Index: 1876130 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7231. Min Range: -5.7231
Max Act: 5.0043. Min Act: -0.1700
Data Index: 6230563 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7231. Min Range: -5.7231
Max Act: 5.0356. Min Act: -0.1700
Data Index: 417887 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.9731. Min Act: -0.1700
Data Index: 2410594 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.9731. Min Act: -0.1700
Data Index: 3193114 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.9418. Min Act: -0.1700
Data Index: 4470787 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.9418. Min Act: -0.1700
Data Index: 2580113 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.9418. Min Act: -0.1700
Data Index: 3708741 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.9106. Min Act: -0.1700
Data Index: 4548250 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.9106. Min Act: -0.1700
Data Index: 6153124 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.9106. Min Act: -0.1700
Data Index: 4792810 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.8481. Min Act: -0.1700
Data Index: 4631417 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.8481. Min Act: -0.1700
Data Index: 3481812 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.8481. Min Act: -0.1700
Data Index: 3370628 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7231. Min Range: -5.7231
Max Act: 4.8481. Min Act: -0.1700
Data Index: 2811812 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19