Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3310. Min Range: -10.3310
Max Act: 10.3310. Min Act: -0.1700
Data Index: 6136543 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3310. Min Range: -10.3310
Max Act: 10.0810. Min Act: -0.1700
Data Index: 6029198 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3310. Min Range: -10.3310
Max Act: 10.0185. Min Act: -0.1700
Data Index: 1674737 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.8935. Min Act: -0.1700
Data Index: 6907587 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.8310. Min Act: -0.1700
Data Index: 8367691 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.8310. Min Act: -0.1700
Data Index: 1674740 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.8310. Min Act: -0.1700
Data Index: 760184 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.7060. Min Act: -0.1700
Data Index: 4046402 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.7685. Min Act: -0.1700
Data Index: 8367687 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.7060. Min Act: -0.1700
Data Index: 4470746 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.7060. Min Act: -0.1700
Data Index: 4753778 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.7060. Min Act: -0.1700
Data Index: 2666811 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.7060. Min Act: -0.1700
Data Index: 8058863 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.7060. Min Act: -0.1700
Data Index: 4817565 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.7060. Min Act: -0.1700
Data Index: 3892397 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.6435. Min Act: -0.1700
Data Index: 2478815 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.6435. Min Act: -0.1700
Data Index: 3012075 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.5810. Min Act: -0.1700
Data Index: 3575924 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.5810. Min Act: -0.1700
Data Index: 2739768 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3310. Min Range: -10.3310
Max Act: 9.5810. Min Act: -0.1700
Data Index: 1797946 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19