Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6058 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.6503. Min Act: -0.1700
Data Index: 5357388 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.4940. Min Act: -0.1700
Data Index: 2233371 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.4628. Min Act: -0.1700
Data Index: 5187435 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.4628. Min Act: -0.1700
Data Index: 854234 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.4003. Min Act: -0.1700
Data Index: 1269357 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.4003. Min Act: -0.1700
Data Index: 4611846 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.3690. Min Act: -0.1700
Data Index: 1629630 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.3378. Min Act: -0.1700
Data Index: 8354265 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.3065. Min Act: -0.1700
Data Index: 3279539 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.3065. Min Act: -0.1700
Data Index: 5945300 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.2753. Min Act: -0.1700
Data Index: 3524139 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.3065. Min Act: -0.1700
Data Index: 3468552 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.3065. Min Act: -0.1700
Data Index: 2277096 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.3065. Min Act: -0.1700
Data Index: 7400889 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.2753. Min Act: -0.1700
Data Index: 5215839 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.2440. Min Act: -0.1700
Data Index: 8141767 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.2440. Min Act: -0.1700
Data Index: 5148552 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.2440. Min Act: -0.1700
Data Index: 7329708 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.2440. Min Act: -0.1700
Data Index: 3142473 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6503. Min Range: -6.6503
Max Act: 6.2440. Min Act: -0.1700
Data Index: 1334089 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19