Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1443 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.5554. Min Act: -0.1700
Data Index: 1703883 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.4616. Min Act: -0.1700
Data Index: 1204875 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.3991. Min Act: -0.1700
Data Index: 724343 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.3366. Min Act: -0.1700
Data Index: 8557834 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.3366. Min Act: -0.1700
Data Index: 1490590 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.3366. Min Act: -0.1700
Data Index: 7939380 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.2741. Min Act: -0.1700
Data Index: 2028044 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.2428. Min Act: -0.1700
Data Index: 163195 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.2428. Min Act: -0.1700
Data Index: 1746313 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.2428. Min Act: -0.1700
Data Index: 4570630 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.2116. Min Act: -0.1700
Data Index: 4609564 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.1803. Min Act: -0.1700
Data Index: 5380974 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.2116. Min Act: -0.1700
Data Index: 1111205 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.2116. Min Act: -0.1700
Data Index: 8628306 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.1803. Min Act: -0.1700
Data Index: 6868010 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.1803. Min Act: -0.1700
Data Index: 3922903 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.1803. Min Act: -0.1700
Data Index: 2699443 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.1491. Min Act: -0.1700
Data Index: 5876523 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.1178. Min Act: -0.1700
Data Index: 3732732 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5554. Min Range: -4.5554
Max Act: 4.1491. Min Act: -0.1700
Data Index: 133624 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19