Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4056. Min Range: -3.4056
Max Act: 3.4056. Min Act: -0.1700
Data Index: 7825734 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4056. Min Range: -3.4056
Max Act: 3.3271. Min Act: -0.1700
Data Index: 7153927 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4056. Min Range: -3.4056
Max Act: 3.2172. Min Act: -0.1700
Data Index: 5904369 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4056. Min Range: -3.4056
Max Act: 3.0597. Min Act: -0.1700
Data Index: 7413376 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4056. Min Range: -3.4056
Max Act: 3.0282. Min Act: -0.1700
Data Index: 7413380 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4056. Min Range: -3.4056
Max Act: 3.0282. Min Act: -0.1700
Data Index: 7413375 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4056. Min Range: -3.4056
Max Act: 3.0282. Min Act: -0.1700
Data Index: 1611575 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4056. Min Range: -3.4056
Max Act: 3.0282. Min Act: -0.1700
Data Index: 3826388 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9966. Min Act: -0.1700
Data Index: 5904368 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4056. Min Range: -3.4056
Max Act: 3.0124. Min Act: -0.1700
Data Index: 7413374 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9966. Min Act: -0.1700
Data Index: 287847 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9966. Min Act: -0.1700
Data Index: 7727089 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9808. Min Act: -0.1699
Data Index: 2884223 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9649. Min Act: -0.1700
Data Index: 287853 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9649. Min Act: -0.1700
Data Index: 715578 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9491. Min Act: -0.1700
Data Index: 8362344 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9333. Min Act: -0.1700
Data Index: 1422675 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9333. Min Act: -0.1700
Data Index: 1910756 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9174. Min Act: -0.1700
Data Index: 1980961 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4056. Min Range: -3.4056
Max Act: 2.9174. Min Act: -0.1700
Data Index: 7466719 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19