Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3990 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.9544. Min Act: -0.1700
Data Index: 7364021 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.7044. Min Act: -0.1700
Data Index: 4319047 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.6731. Min Act: -0.1700
Data Index: 2026901 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.6419. Min Act: -0.1700
Data Index: 53210 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.6106. Min Act: -0.1700
Data Index: 5694725 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.6106. Min Act: -0.1700
Data Index: 2358030 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.5794. Min Act: -0.1700
Data Index: 8698413 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.5794. Min Act: -0.1700
Data Index: 3559688 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.5794. Min Act: -0.1700
Data Index: 2838474 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.5169. Min Act: -0.1700
Data Index: 6139250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.4231. Min Act: -0.1700
Data Index: 4190973 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.4231. Min Act: -0.1700
Data Index: 5557742 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.4231. Min Act: -0.1700
Data Index: 2312597 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.4231. Min Act: -0.1700
Data Index: 5558195 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.4231. Min Act: -0.1700
Data Index: 8393891 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.4231. Min Act: -0.1700
Data Index: 2877687 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.4231. Min Act: -0.1700
Data Index: 356435 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.3919. Min Act: -0.1700
Data Index: 7520709 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.3919. Min Act: -0.1700
Data Index: 5938699 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9544. Min Range: -6.9544
Max Act: 6.3606. Min Act: -0.1700
Data Index: 882173 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19