Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.7304. Min Act: -0.1700
Data Index: 2408744 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.6985. Min Act: -0.1700
Data Index: 5885817 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.6504. Min Act: -0.1700
Data Index: 8487973 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.6504. Min Act: -0.1700
Data Index: 1660326 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.6343. Min Act: -0.1700
Data Index: 1934559 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.6183. Min Act: -0.1700
Data Index: 333690 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.6183. Min Act: -0.1700
Data Index: 2993469 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.6022. Min Act: -0.1700
Data Index: 7640286 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.5861. Min Act: -0.1700
Data Index: 6367593 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.6022. Min Act: -0.1700
Data Index: 5061886 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.6022. Min Act: -0.1700
Data Index: 5698953 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.6022. Min Act: -0.1700
Data Index: 4739609 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.5861. Min Act: -0.1700
Data Index: 1214921 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.5861. Min Act: -0.1700
Data Index: 984600 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.5861. Min Act: -0.1700
Data Index: 8614398 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.5861. Min Act: -0.1700
Data Index: 4849025 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.5538. Min Act: -0.1700
Data Index: 7193042 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.5538. Min Act: -0.1700
Data Index: 4103510 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.5538. Min Act: -0.1700
Data Index: 6260818 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7304. Min Range: -2.7304
Max Act: 2.5377. Min Act: -0.1700
Data Index: 2811719 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19