Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4924 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.6688. Min Act: -0.1700
Data Index: 7194517 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.4813. Min Act: -0.1700
Data Index: 1957233 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.4813. Min Act: -0.1700
Data Index: 1858866 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.4188. Min Act: -0.1700
Data Index: 2145962 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.4188. Min Act: -0.1700
Data Index: 3581873 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.3563. Min Act: -0.1700
Data Index: 6568729 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.3563. Min Act: -0.1700
Data Index: 6581553 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2938. Min Act: -0.1700
Data Index: 1808334 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2938. Min Act: -0.1700
Data Index: 4740314 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2938. Min Act: -0.1700
Data Index: 477097 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2938. Min Act: -0.1700
Data Index: 6720074 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2938. Min Act: -0.1700
Data Index: 7216317 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2938. Min Act: -0.1700
Data Index: 6390095 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2313. Min Act: -0.1700
Data Index: 4805627 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2313. Min Act: -0.1700
Data Index: 6929846 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2313. Min Act: -0.1700
Data Index: 473014 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2313. Min Act: -0.1700
Data Index: 7361007 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.2313. Min Act: -0.1700
Data Index: 4302940 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.1688. Min Act: -0.1700
Data Index: 4098729 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6688. Min Range: -9.6688
Max Act: 9.1688. Min Act: -0.1700
Data Index: 2174465 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19