Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.7351. Min Act: -0.1700
Data Index: 2489967 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.7039. Min Act: -0.1700
Data Index: 8810555 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6414. Min Act: -0.1700
Data Index: 3741507 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5788. Min Act: -0.1700
Data Index: 3420638 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 8213278 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 558140 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5163. Min Act: -0.1700
Data Index: 5705642 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.4851. Min Act: -0.1700
Data Index: 8501105 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.4851. Min Act: -0.1700
Data Index: 168194 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.4538. Min Act: -0.1700
Data Index: 285175 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.4226. Min Act: -0.1700
Data Index: 4399740 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.4226. Min Act: -0.1700
Data Index: 8403776 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.4226. Min Act: -0.1700
Data Index: 5583598 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.4226. Min Act: -0.1700
Data Index: 7793265 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.3913. Min Act: -0.1700
Data Index: 8408942 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.3913. Min Act: -0.1700
Data Index: 5547119 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.3601. Min Act: -0.1700
Data Index: 6730639 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.3288. Min Act: -0.1700
Data Index: 7855412 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.3288. Min Act: -0.1700
Data Index: 2740877 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.3288. Min Act: -0.1700
Data Index: 7235487 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19