Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5983 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.6348. Min Act: -0.1700
Data Index: 1256997 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.5411. Min Act: -0.1700
Data Index: 91166 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.3536. Min Act: -0.1700
Data Index: 6987555 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1973. Min Act: -0.1700
Data Index: 862546 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.2286. Min Act: -0.1700
Data Index: 3068782 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1661. Min Act: -0.1700
Data Index: 7763705 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1661. Min Act: -0.1700
Data Index: 7953144 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.0723. Min Act: -0.1700
Data Index: 7760598 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.0723. Min Act: -0.1700
Data Index: 5929686 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.0098. Min Act: -0.1700
Data Index: 7030995 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.0411. Min Act: -0.1700
Data Index: 3943051 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.0098. Min Act: -0.1700
Data Index: 7471734 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.0098. Min Act: -0.1700
Data Index: 6737237 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.0098. Min Act: -0.1700
Data Index: 4368105 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6348. Min Range: -6.6348
Max Act: 5.9473. Min Act: -0.1700
Data Index: 7230083 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6348. Min Range: -6.6348
Max Act: 5.9473. Min Act: -0.1700
Data Index: 8474892 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6348. Min Range: -6.6348
Max Act: 5.9473. Min Act: -0.1700
Data Index: 6154940 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6348. Min Range: -6.6348
Max Act: 5.9473. Min Act: -0.1700
Data Index: 1175546 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6348. Min Range: -6.6348
Max Act: 5.9161. Min Act: -0.1700
Data Index: 6300550 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6348. Min Range: -6.6348
Max Act: 5.9473. Min Act: -0.1700
Data Index: 2012351 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19