Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 189 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0483. Min Range: -9.0483
Max Act: 9.0483. Min Act: -0.1700
Data Index: 3507975 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.6733. Min Act: -0.1700
Data Index: 1060725 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.4858. Min Act: -0.1700
Data Index: 5141023 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.4858. Min Act: -0.1700
Data Index: 1330115 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.4858. Min Act: -0.1700
Data Index: 7959811 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.3608. Min Act: -0.1700
Data Index: 696634 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.3608. Min Act: -0.1700
Data Index: 2204003 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.2983. Min Act: -0.1700
Data Index: 287036 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.2358. Min Act: -0.1700
Data Index: 3024245 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.2358. Min Act: -0.1700
Data Index: 4613810 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.1733. Min Act: -0.1700
Data Index: 4899771 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.1733. Min Act: -0.1700
Data Index: 8588256 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.1733. Min Act: -0.1700
Data Index: 6467417 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.1733. Min Act: -0.1700
Data Index: 294421 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.1733. Min Act: -0.1700
Data Index: 526468 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.1108. Min Act: -0.1700
Data Index: 566424 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.1108. Min Act: -0.1700
Data Index: 2543208 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.1108. Min Act: -0.1700
Data Index: 7501992 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.1108. Min Act: -0.1700
Data Index: 5018211 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0483. Min Range: -9.0483
Max Act: 8.1108. Min Act: -0.1700
Data Index: 389734 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19