Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5942 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.2630. Min Act: -0.1700
Data Index: 4292327 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.2317. Min Act: -0.1700
Data Index: 6497367 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.2317. Min Act: -0.1700
Data Index: 6919376 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.2317. Min Act: -0.1700
Data Index: 4089318 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.2630. Min Act: -0.1700
Data Index: 5393510 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.2317. Min Act: -0.1700
Data Index: 8471533 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1692. Min Act: -0.1700
Data Index: 2356625 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1692. Min Act: -0.1700
Data Index: 945612 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1692. Min Act: -0.1700
Data Index: 4448056 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1692. Min Act: -0.1700
Data Index: 1949509 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1692. Min Act: -0.1700
Data Index: 5516512 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1067. Min Act: -0.1700
Data Index: 8310033 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 5867333 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 5832549 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 8376197 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 2477996 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 6669434 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 2296782 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 3229146 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2630. Min Range: -5.2630
Max Act: 5.0755. Min Act: -0.1700
Data Index: 2820187 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19