Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2362. Min Range: -6.2362
Max Act: 6.2362. Min Act: -0.1700
Data Index: 5004397 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2362. Min Range: -6.2362
Max Act: 6.1112. Min Act: -0.1700
Data Index: 8263511 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2362. Min Range: -6.2362
Max Act: 6.0800. Min Act: -0.1700
Data Index: 915780 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2362. Min Range: -6.2362
Max Act: 6.0487. Min Act: -0.1700
Data Index: 6636614 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2362. Min Range: -6.2362
Max Act: 6.0800. Min Act: -0.1700
Data Index: 8158036 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2362. Min Range: -6.2362
Max Act: 6.0487. Min Act: -0.1700
Data Index: 6222342 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2362. Min Range: -6.2362
Max Act: 6.0487. Min Act: -0.1700
Data Index: 2353997 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2362. Min Range: -6.2362
Max Act: 6.0175. Min Act: -0.1700
Data Index: 645990 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2362. Min Range: -6.2362
Max Act: 6.0175. Min Act: -0.1700
Data Index: 2581767 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9550. Min Act: -0.1700
Data Index: 8639612 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9862. Min Act: -0.1700
Data Index: 3738923 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9862. Min Act: -0.1700
Data Index: 8668916 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9862. Min Act: -0.1699
Data Index: 1956075 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9550. Min Act: -0.1700
Data Index: 1944004 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9550. Min Act: -0.1700
Data Index: 7117998 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9862. Min Act: -0.1700
Data Index: 5576051 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9550. Min Act: -0.1700
Data Index: 2582865 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9550. Min Act: -0.1700
Data Index: 1511084 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9237. Min Act: -0.1700
Data Index: 6130986 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2362. Min Range: -6.2362
Max Act: 5.9550. Min Act: -0.1700
Data Index: 3649090 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19