Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4936 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1320. Min Range: -6.1320
Max Act: 6.1320. Min Act: -0.1700
Data Index: 4800189 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.9758. Min Act: -0.1700
Data Index: 121497 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.8508. Min Act: -0.1700
Data Index: 1899877 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.7570. Min Act: -0.1700
Data Index: 2299476 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.6945. Min Act: -0.1700
Data Index: 1831671 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.6633. Min Act: -0.1700
Data Index: 1176725 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.6320. Min Act: -0.1700
Data Index: 244789 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.6320. Min Act: -0.1700
Data Index: 8471311 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.5695. Min Act: -0.1700
Data Index: 3905200 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.5695. Min Act: -0.1700
Data Index: 7639727 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.5695. Min Act: -0.1700
Data Index: 7874994 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 8766654 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 6595023 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 801088 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 8769740 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 7965369 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.4758. Min Act: -0.1700
Data Index: 8718912 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.4758. Min Act: -0.1700
Data Index: 2184487 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.5070. Min Act: -0.1700
Data Index: 1473605 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1320. Min Range: -6.1320
Max Act: 5.5383. Min Act: -0.1700
Data Index: 1508570 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19