Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4405 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4153. Min Range: -6.4153
Max Act: 6.4153. Min Act: -0.1700
Data Index: 372015 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4153. Min Range: -6.4153
Max Act: 6.2903. Min Act: -0.1700
Data Index: 3822477 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4153. Min Range: -6.4153
Max Act: 6.2903. Min Act: -0.1700
Data Index: 5535248 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4153. Min Range: -6.4153
Max Act: 6.2590. Min Act: -0.1700
Data Index: 3822480 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4153. Min Range: -6.4153
Max Act: 6.0715. Min Act: -0.1700
Data Index: 3824005 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4153. Min Range: -6.4153
Max Act: 6.0090. Min Act: -0.1700
Data Index: 4436837 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4153. Min Range: -6.4153
Max Act: 6.0403. Min Act: -0.1700
Data Index: 2601344 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4153. Min Range: -6.4153
Max Act: 6.0090. Min Act: -0.1700
Data Index: 2832261 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4153. Min Range: -6.4153
Max Act: 6.0090. Min Act: -0.1700
Data Index: 351414 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4153. Min Range: -6.4153
Max Act: 6.0090. Min Act: -0.1700
Data Index: 5505575 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4153. Min Range: -6.4153
Max Act: 5.9778. Min Act: -0.1700
Data Index: 6910602 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4153. Min Range: -6.4153
Max Act: 5.9778. Min Act: -0.1700
Data Index: 7524453 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4153. Min Range: -6.4153
Max Act: 5.9778. Min Act: -0.1700
Data Index: 6131268 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4153. Min Range: -6.4153
Max Act: 5.9778. Min Act: -0.1700
Data Index: 351413 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4153. Min Range: -6.4153
Max Act: 5.9778. Min Act: -0.1700
Data Index: 3012233 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4153. Min Range: -6.4153
Max Act: 5.9153. Min Act: -0.1700
Data Index: 2058985 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4153. Min Range: -6.4153
Max Act: 5.9465. Min Act: -0.1700
Data Index: 5497698 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4153. Min Range: -6.4153
Max Act: 5.9465. Min Act: -0.1700
Data Index: 2045558 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4153. Min Range: -6.4153
Max Act: 5.9465. Min Act: -0.1700
Data Index: 6014857 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4153. Min Range: -6.4153
Max Act: 5.9465. Min Act: -0.1700
Data Index: 5671773 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19