Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.5076. Min Act: -0.1700
Data Index: 1047963 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.2889. Min Act: -0.1700
Data Index: 4987321 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.2264. Min Act: -0.1700
Data Index: 2067364 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.2264. Min Act: -0.1700
Data Index: 4630127 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.2264. Min Act: -0.1700
Data Index: 4997703 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.1639. Min Act: -0.1700
Data Index: 7325115 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.1951. Min Act: -0.1700
Data Index: 7160813 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.1639. Min Act: -0.1700
Data Index: 7403454 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.1326. Min Act: -0.1700
Data Index: 4479958 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.1326. Min Act: -0.1700
Data Index: 540901 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.1639. Min Act: -0.1700
Data Index: 2826781 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.1326. Min Act: -0.1700
Data Index: 8797073 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.1326. Min Act: -0.1700
Data Index: 8455281 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.1014. Min Act: -0.1700
Data Index: 7907416 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.0701. Min Act: -0.1700
Data Index: 6655079 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.0389. Min Act: -0.1700
Data Index: 2152610 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.0389. Min Act: -0.1700
Data Index: 2442039 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.0389. Min Act: -0.1700
Data Index: 7037664 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5076. Min Range: -6.5076
Max Act: 6.0076. Min Act: -0.1700
Data Index: 3861556 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5076. Min Range: -6.5076
Max Act: 5.9764. Min Act: -0.1700
Data Index: 3493944 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19