Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5501 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.9161. Min Act: -0.1700
Data Index: 1069635 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.6973. Min Act: -0.1700
Data Index: 452011 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.4786. Min Act: -0.1700
Data Index: 3808492 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.4473. Min Act: -0.1700
Data Index: 218569 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.3848. Min Act: -0.1700
Data Index: 5966909 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.3223. Min Act: -0.1700
Data Index: 2424222 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.3223. Min Act: -0.1700
Data Index: 2703251 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.2911. Min Act: -0.1700
Data Index: 4108540 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.2911. Min Act: -0.1700
Data Index: 2703249 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.2598. Min Act: -0.1700
Data Index: 1277870 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.3223. Min Act: -0.1700
Data Index: 2424223 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.1661. Min Act: -0.1700
Data Index: 2424219 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.1661. Min Act: -0.1700
Data Index: 2703246 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.1661. Min Act: -0.1700
Data Index: 6245361 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.1661. Min Act: -0.1700
Data Index: 5966904 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.1661. Min Act: -0.1700
Data Index: 2424220 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.1348. Min Act: -0.1700
Data Index: 1633562 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.1036. Min Act: -0.1700
Data Index: 1585926 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.1036. Min Act: -0.1700
Data Index: 2606587 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9161. Min Range: -6.9161
Max Act: 6.1036. Min Act: -0.1700
Data Index: 5721394 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19