Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6712. Min Range: -11.6712
Max Act: 11.6712. Min Act: -0.1700
Data Index: 6648936 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6712. Min Range: -11.6712
Max Act: 11.5462. Min Act: -0.1700
Data Index: 4764453 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6712. Min Range: -11.6712
Max Act: 11.4212. Min Act: -0.1700
Data Index: 7978448 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6712. Min Range: -11.6712
Max Act: 11.1712. Min Act: -0.1700
Data Index: 8333135 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6712. Min Range: -11.6712
Max Act: 11.1087. Min Act: -0.1700
Data Index: 5701894 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.9837. Min Act: -0.1700
Data Index: 6323232 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.9212. Min Act: -0.1700
Data Index: 8437830 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.9212. Min Act: -0.1700
Data Index: 5543559 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.9212. Min Act: -0.1700
Data Index: 7502932 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.9212. Min Act: -0.1700
Data Index: 1102976 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.9212. Min Act: -0.1700
Data Index: 7711146 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.8587. Min Act: -0.1700
Data Index: 4985077 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.8587. Min Act: -0.1700
Data Index: 5491775 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.8587. Min Act: -0.1700
Data Index: 500490 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.8587. Min Act: -0.1700
Data Index: 4609772 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.7962. Min Act: -0.1700
Data Index: 3175771 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.7962. Min Act: -0.1700
Data Index: 1849581 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.8587. Min Act: -0.1700
Data Index: 5904804 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.7962. Min Act: -0.1700
Data Index: 6752148 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6712. Min Range: -11.6712
Max Act: 10.7337. Min Act: -0.1700
Data Index: 2394262 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19