Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1382. Min Range: -5.1382
Max Act: 5.1382. Min Act: -0.1700
Data Index: 7276038 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.7319. Min Act: -0.1700
Data Index: 99408 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.7007. Min Act: -0.1700
Data Index: 8128167 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.6069. Min Act: -0.1700
Data Index: 2907872 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.5757. Min Act: -0.1700
Data Index: 1110100 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.5132. Min Act: -0.1700
Data Index: 31754 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.4819. Min Act: -0.1700
Data Index: 215013 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.4194. Min Act: -0.1700
Data Index: 1256891 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.3882. Min Act: -0.1700
Data Index: 8128169 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.3569. Min Act: -0.1700
Data Index: 8000615 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.3569. Min Act: -0.1700
Data Index: 5684035 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.3569. Min Act: -0.1700
Data Index: 7491510 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.2944. Min Act: -0.1700
Data Index: 2811446 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.2632. Min Act: -0.1700
Data Index: 3285834 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.2319. Min Act: -0.1700
Data Index: 4988759 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.2319. Min Act: -0.1700
Data Index: 3936123 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.2319. Min Act: -0.1700
Data Index: 4831132 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.2007. Min Act: -0.1700
Data Index: 8588371 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.2319. Min Act: -0.1700
Data Index: 8098694 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1382. Min Range: -5.1382
Max Act: 4.1694. Min Act: -0.1700
Data Index: 6113822 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19