Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.7399. Min Act: -0.1700
Data Index: 7654113 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.6774. Min Act: -0.1700
Data Index: 2382853 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.4586. Min Act: -0.1700
Data Index: 8110359 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.3024. Min Act: -0.1700
Data Index: 5281955 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.3024. Min Act: -0.1700
Data Index: 1678192 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.2711. Min Act: -0.1700
Data Index: 5253473 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.2399. Min Act: -0.1700
Data Index: 8331653 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.2399. Min Act: -0.1700
Data Index: 7348 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.2086. Min Act: -0.1700
Data Index: 5551205 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.2086. Min Act: -0.1700
Data Index: 5688673 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.1774. Min Act: -0.1700
Data Index: 837759 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.1774. Min Act: -0.1700
Data Index: 6763657 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.1461. Min Act: -0.1700
Data Index: 6081911 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.1461. Min Act: -0.1700
Data Index: 5982439 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.1461. Min Act: -0.1700
Data Index: 3412870 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.1461. Min Act: -0.1700
Data Index: 8651105 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.1149. Min Act: -0.1700
Data Index: 7974468 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.1149. Min Act: -0.1700
Data Index: 5008258 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.1149. Min Act: -0.1700
Data Index: 1131394 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7399. Min Range: -5.7399
Max Act: 5.1149. Min Act: -0.1700
Data Index: 8013566 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19