Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2156. Min Range: -5.2156
Max Act: 5.2156. Min Act: -0.1700
Data Index: 823424 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2156. Min Range: -5.2156
Max Act: 5.1843. Min Act: -0.1700
Data Index: 1824622 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2156. Min Range: -5.2156
Max Act: 5.0281. Min Act: -0.1700
Data Index: 1988566 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2156. Min Range: -5.2156
Max Act: 5.0593. Min Act: -0.1700
Data Index: 5194271 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2156. Min Range: -5.2156
Max Act: 5.0593. Min Act: -0.1700
Data Index: 2371486 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2156. Min Range: -5.2156
Max Act: 5.0281. Min Act: -0.1700
Data Index: 2371487 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9656. Min Act: -0.1700
Data Index: 915605 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9656. Min Act: -0.1700
Data Index: 3335402 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9343. Min Act: -0.1700
Data Index: 5195626 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9031. Min Act: -0.1700
Data Index: 6799320 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9343. Min Act: -0.1700
Data Index: 1659830 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9343. Min Act: -0.1700
Data Index: 2118139 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9343. Min Act: -0.1700
Data Index: 4343831 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9031. Min Act: -0.1700
Data Index: 5134049 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8718. Min Act: -0.1700
Data Index: 576856 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8718. Min Act: -0.1700
Data Index: 8133167 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8718. Min Act: -0.1700
Data Index: 6454673 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8406. Min Act: -0.1700
Data Index: 5220166 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8406. Min Act: -0.1700
Data Index: 4180737 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8406. Min Act: -0.1700
Data Index: 7872961 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19