Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.9656. Min Act: -0.1700
Data Index: 8333829 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.9656. Min Act: -0.1700
Data Index: 133988 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.9344. Min Act: -0.1700
Data Index: 6146804 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.7781. Min Act: -0.1700
Data Index: 2584665 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.7156. Min Act: -0.1700
Data Index: 7105424 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.7156. Min Act: -0.1700
Data Index: 6434978 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.6844. Min Act: -0.1700
Data Index: 543253 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.6844. Min Act: -0.1488
Data Index: 919008 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.6531. Min Act: -0.1700
Data Index: 6017276 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.6219. Min Act: -0.1576
Data Index: 6400795 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.6531. Min Act: -0.1700
Data Index: 3051881 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.6219. Min Act: -0.1691
Data Index: 8482164 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.5594. Min Act: -0.1666
Data Index: 918991 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.5906. Min Act: -0.1698
Data Index: 1547376 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.5594. Min Act: -0.1700
Data Index: 1986940 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.5594. Min Act: -0.1662
Data Index: 1204125 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.5594. Min Act: -0.1700
Data Index: 6400796 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.5594. Min Act: -0.1697
Data Index: 919010 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.5594. Min Act: -0.1700
Data Index: 3128704 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9656. Min Range: -6.9656
Max Act: 6.5594. Min Act: -0.1700
Data Index: 2584672 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19