Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1434. Min Range: -3.1434
Max Act: 3.1434. Min Act: -0.1700
Data Index: 6815980 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1434. Min Range: -3.1434
Max Act: 3.0488. Min Act: -0.1700
Data Index: 1132152 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1434. Min Range: -3.1434
Max Act: 3.0330. Min Act: -0.1700
Data Index: 6837774 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1434. Min Range: -3.1434
Max Act: 3.0488. Min Act: -0.1700
Data Index: 8658792 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1434. Min Range: -3.1434
Max Act: 3.0172. Min Act: -0.1700
Data Index: 1799401 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9856. Min Act: -0.1700
Data Index: 4700136 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9856. Min Act: -0.1700
Data Index: 5441364 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9698. Min Act: -0.1700
Data Index: 5733772 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9698. Min Act: -0.1700
Data Index: 2019892 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9698. Min Act: -0.1700
Data Index: 3294976 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9698. Min Act: -0.1700
Data Index: 313075 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9540. Min Act: -0.1700
Data Index: 6492777 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9540. Min Act: -0.1700
Data Index: 4132583 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9540. Min Act: -0.1700
Data Index: 3197810 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9540. Min Act: -0.1700
Data Index: 3566975 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9381. Min Act: -0.1700
Data Index: 2283188 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9381. Min Act: -0.1700
Data Index: 623977 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9223. Min Act: -0.1700
Data Index: 7729469 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9223. Min Act: -0.1700
Data Index: 3702735 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1434. Min Range: -3.1434
Max Act: 2.9223. Min Act: -0.1700
Data Index: 1334282 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19