Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2406. Min Range: -7.2406
Max Act: 7.2406. Min Act: -0.1700
Data Index: 1424416 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.9594. Min Act: -0.1700
Data Index: 5167067 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.7719. Min Act: -0.1700
Data Index: 7921837 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.7094. Min Act: -0.1700
Data Index: 1343751 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.6469. Min Act: -0.1700
Data Index: 5102031 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.5531. Min Act: -0.1700
Data Index: 3025889 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.5844. Min Act: -0.1700
Data Index: 5376401 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.5219. Min Act: -0.1700
Data Index: 3702428 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.5844. Min Act: -0.1700
Data Index: 3752289 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.5531. Min Act: -0.1700
Data Index: 3500508 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.5219. Min Act: -0.1700
Data Index: 3299850 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.5219. Min Act: -0.1700
Data Index: 2677135 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.5219. Min Act: -0.1700
Data Index: 5219187 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.4594. Min Act: -0.1700
Data Index: 5662455 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.4594. Min Act: -0.1700
Data Index: 297918 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.4281. Min Act: -0.1700
Data Index: 4874601 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.3656. Min Act: -0.1700
Data Index: 120444 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.3344. Min Act: -0.1700
Data Index: 2930717 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.3344. Min Act: -0.1700
Data Index: 6010560 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2406. Min Range: -7.2406
Max Act: 6.3344. Min Act: -0.1700
Data Index: 7010730 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19