Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 783 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.4378. Min Act: -0.1700
Data Index: 2105939 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.4066. Min Act: -0.1700
Data Index: 2710938 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.2503. Min Act: -0.1700
Data Index: 3766838 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.1878. Min Act: -0.1700
Data Index: 2523728 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.1878. Min Act: -0.1700
Data Index: 4459093 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.1253. Min Act: -0.1700
Data Index: 3995989 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0941. Min Act: -0.1700
Data Index: 3292202 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0941. Min Act: -0.1700
Data Index: 5121404 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0628. Min Act: -0.1700
Data Index: 1946701 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0316. Min Act: -0.1700
Data Index: 957592 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0628. Min Act: -0.1700
Data Index: 7680418 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0628. Min Act: -0.1700
Data Index: 3370486 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0316. Min Act: -0.1700
Data Index: 7019931 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0316. Min Act: -0.1700
Data Index: 1732658 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0316. Min Act: -0.1700
Data Index: 1481865 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0003. Min Act: -0.1700
Data Index: 6225015 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0003. Min Act: -0.1700
Data Index: 5484560 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0003. Min Act: -0.1700
Data Index: 4542154 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4378. Min Range: -5.4378
Max Act: 5.0003. Min Act: -0.1700
Data Index: 3284546 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4378. Min Range: -5.4378
Max Act: 4.9691. Min Act: -0.1700
Data Index: 6337452 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19