Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1357. Min Range: -4.1357
Max Act: 4.1357. Min Act: -0.1700
Data Index: 1620368 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1357. Min Range: -4.1357
Max Act: 4.0420. Min Act: -0.1700
Data Index: 4966282 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1357. Min Range: -4.1357
Max Act: 4.0107. Min Act: -0.1700
Data Index: 1204015 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.9795. Min Act: -0.1700
Data Index: 356989 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.9482. Min Act: -0.1700
Data Index: 6394207 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.9013. Min Act: -0.1700
Data Index: 2220522 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.9169. Min Act: -0.1700
Data Index: 3188307 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.9169. Min Act: -0.1700
Data Index: 8692391 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.9013. Min Act: -0.1700
Data Index: 1890948 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8700. Min Act: -0.1700
Data Index: 6876752 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8857. Min Act: -0.1700
Data Index: 1886036 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8700. Min Act: -0.1700
Data Index: 4207547 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8544. Min Act: -0.1700
Data Index: 769598 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8544. Min Act: -0.1700
Data Index: 3512151 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8544. Min Act: -0.1700
Data Index: 2036271 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8544. Min Act: -0.1700
Data Index: 8430070 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8231. Min Act: -0.1700
Data Index: 7149796 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8231. Min Act: -0.1700
Data Index: 7051021 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8231. Min Act: -0.1700
Data Index: 4910494 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1357. Min Range: -4.1357
Max Act: 3.8075. Min Act: -0.1700
Data Index: 3199876 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19