Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1519 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0315. Min Range: -5.0315
Max Act: 5.0315. Min Act: -0.1700
Data Index: 6842016 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.7815. Min Act: -0.1700
Data Index: 446579 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.7502. Min Act: -0.1700
Data Index: 2802844 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.7502. Min Act: -0.1700
Data Index: 8095734 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.7502. Min Act: -0.1700
Data Index: 6747653 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.7190. Min Act: -0.1700
Data Index: 6849695 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.7190. Min Act: -0.1700
Data Index: 4333543 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6877. Min Act: -0.1700
Data Index: 5114621 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6877. Min Act: -0.1700
Data Index: 8400312 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6877. Min Act: -0.1700
Data Index: 541 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6877. Min Act: -0.1700
Data Index: 2240762 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6877. Min Act: -0.1700
Data Index: 4824496 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6565. Min Act: -0.1700
Data Index: 2888400 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6565. Min Act: -0.1700
Data Index: 547 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6565. Min Act: -0.1700
Data Index: 1864065 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6252. Min Act: -0.1700
Data Index: 2802856 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6252. Min Act: -0.1700
Data Index: 5642563 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6252. Min Act: -0.1700
Data Index: 2345069 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.5940. Min Act: -0.1700
Data Index: 2041944 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0315. Min Range: -5.0315
Max Act: 4.6252. Min Act: -0.1700
Data Index: 3552727 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19