Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2623 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.5122. Min Act: -0.1700
Data Index: 4480815 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.4497. Min Act: -0.1700
Data Index: 3051612 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.4185. Min Act: -0.1700
Data Index: 4261030 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.3872. Min Act: -0.1700
Data Index: 6578056 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.3560. Min Act: -0.1700
Data Index: 2307598 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.2622. Min Act: -0.1700
Data Index: 4986431 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.2310. Min Act: -0.1700
Data Index: 2164379 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.2310. Min Act: -0.1700
Data Index: 4113096 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1997. Min Act: -0.1700
Data Index: 7583497 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1685. Min Act: -0.1700
Data Index: 2193011 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1372. Min Act: -0.1700
Data Index: 8530682 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1372. Min Act: -0.1700
Data Index: 2028987 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1372. Min Act: -0.1700
Data Index: 5085960 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1372. Min Act: -0.1700
Data Index: 2021368 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.0747. Min Act: -0.1700
Data Index: 6456801 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1060. Min Act: -0.1700
Data Index: 8015720 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.0747. Min Act: -0.1700
Data Index: 7411116 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.0747. Min Act: -0.1700
Data Index: 1868931 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.0747. Min Act: -0.1700
Data Index: 1910353 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1060. Min Act: -0.1700
Data Index: 3695018 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19