Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 135 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.9183. Min Act: -0.1700
Data Index: 8662656 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.9183. Min Act: -0.1700
Data Index: 2076591 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.9183. Min Act: -0.1700
Data Index: 2136299 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.8870. Min Act: -0.1700
Data Index: 7475780 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.8245. Min Act: -0.1700
Data Index: 6567468 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.7308. Min Act: -0.1700
Data Index: 7817205 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.7620. Min Act: -0.1700
Data Index: 5020336 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.6995. Min Act: -0.1700
Data Index: 7661498 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.6995. Min Act: -0.1700
Data Index: 3730418 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.6995. Min Act: -0.1700
Data Index: 3856798 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.6058. Min Act: -0.1700
Data Index: 736388 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.6370. Min Act: -0.1700
Data Index: 1525029 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.5745. Min Act: -0.1700
Data Index: 7475779 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.5745. Min Act: -0.1700
Data Index: 4645830 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.5433. Min Act: -0.1700
Data Index: 7965775 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.5120. Min Act: -0.1700
Data Index: 6422436 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.5120. Min Act: -0.1700
Data Index: 1921650 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.5433. Min Act: -0.1700
Data Index: 4811433 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.5120. Min Act: -0.1700
Data Index: 7280599 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9183. Min Range: -7.9183
Max Act: 7.5433. Min Act: -0.1700
Data Index: 3989296 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19