Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 412 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.7202. Min Act: -0.1700
Data Index: 3681862 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.7042. Min Act: -0.1700
Data Index: 3697145 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.7042. Min Act: -0.1700
Data Index: 4694047 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.6882. Min Act: -0.1700
Data Index: 4005631 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.6882. Min Act: -0.1700
Data Index: 8570025 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.6561. Min Act: -0.1700
Data Index: 441378 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.6240. Min Act: -0.1700
Data Index: 424139 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.6401. Min Act: -0.1700
Data Index: 7946703 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.6240. Min Act: -0.1700
Data Index: 7117399 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.6240. Min Act: -0.1700
Data Index: 5494664 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.6079. Min Act: -0.1700
Data Index: 182638 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.5918. Min Act: -0.1700
Data Index: 2408660 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.5918. Min Act: -0.1700
Data Index: 578589 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.5918. Min Act: -0.1700
Data Index: 2492960 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.5757. Min Act: -0.1700
Data Index: 410171 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.5757. Min Act: -0.1700
Data Index: 5004471 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.5757. Min Act: -0.1700
Data Index: 5004473 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.5757. Min Act: -0.1700
Data Index: 8257765 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.5918. Min Act: -0.1700
Data Index: 6898034 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7202. Min Range: -2.7202
Max Act: 2.5918. Min Act: -0.1700
Data Index: 6490508 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19