Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 103 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.9010. Min Act: -0.1700
Data Index: 4804446 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.9010. Min Act: -0.1700
Data Index: 53044 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.9010. Min Act: -0.1700
Data Index: 6932713 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.7760. Min Act: -0.1700
Data Index: 6384001 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.5260. Min Act: -0.1700
Data Index: 435239 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.5260. Min Act: -0.1700
Data Index: 6869500 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.4948. Min Act: -0.1700
Data Index: 8284322 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.4948. Min Act: -0.1700
Data Index: 2570252 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.4948. Min Act: -0.1700
Data Index: 1890546 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.4635. Min Act: -0.1700
Data Index: 7560288 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.4323. Min Act: -0.1700
Data Index: 2639523 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.4010. Min Act: -0.1700
Data Index: 40246 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.4323. Min Act: -0.1700
Data Index: 3153477 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.4010. Min Act: -0.1700
Data Index: 2006680 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.4010. Min Act: -0.1700
Data Index: 7367782 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.3385. Min Act: -0.1700
Data Index: 2966577 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.3698. Min Act: -0.1700
Data Index: 2370589 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.3698. Min Act: -0.1700
Data Index: 3943046 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.3385. Min Act: -0.1700
Data Index: 829598 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9010. Min Range: -5.9010
Max Act: 5.3385. Min Act: -0.1700
Data Index: 7550265 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19