Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.2709. Min Act: -0.1700
Data Index: 3039731 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.2084. Min Act: -0.1700
Data Index: 1735466 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.1146. Min Act: -0.1700
Data Index: 6654226 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 3039732 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9271. Min Act: -0.1700
Data Index: 3657316 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8959. Min Act: -0.1700
Data Index: 3528423 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8646. Min Act: -0.1700
Data Index: 6764363 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8334. Min Act: -0.1700
Data Index: 2288645 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8334. Min Act: -0.1700
Data Index: 799565 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8334. Min Act: -0.1700
Data Index: 1624716 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8021. Min Act: -0.1700
Data Index: 2552282 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8334. Min Act: -0.1700
Data Index: 7560545 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8021. Min Act: -0.1700
Data Index: 2490224 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.7709. Min Act: -0.1700
Data Index: 2717444 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.7709. Min Act: -0.1700
Data Index: 4731756 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.7709. Min Act: -0.1700
Data Index: 2215987 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8021. Min Act: -0.1700
Data Index: 6047621 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.7396. Min Act: -0.1700
Data Index: 4289789 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.7396. Min Act: -0.1700
Data Index: 4722689 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.7396. Min Act: -0.1700
Data Index: 886979 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19