Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2036 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.9816. Min Act: -0.1700
Data Index: 3059869 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.9191. Min Act: -0.1700
Data Index: 4800224 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.7941. Min Act: -0.1700
Data Index: 5012266 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.7316. Min Act: -0.1700
Data Index: 7383714 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.5441. Min Act: -0.1700
Data Index: 7545667 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.4816. Min Act: -0.1700
Data Index: 4885938 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.4191. Min Act: -0.1700
Data Index: 6376466 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.4191. Min Act: -0.1700
Data Index: 3552968 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2941. Min Act: -0.1700
Data Index: 6514452 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2941. Min Act: -0.1700
Data Index: 6445536 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2316. Min Act: -0.1700
Data Index: 7480397 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2316. Min Act: -0.1700
Data Index: 4344327 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2316. Min Act: -0.1700
Data Index: 2112994 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2316. Min Act: -0.1700
Data Index: 2106033 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2629. Min Act: -0.1700
Data Index: 6391399 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2316. Min Act: -0.1700
Data Index: 8567930 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2004. Min Act: -0.1700
Data Index: 7310804 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2004. Min Act: -0.1700
Data Index: 2382888 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.2004. Min Act: -0.1700
Data Index: 635006 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9816. Min Range: -8.9816
Max Act: 8.1379. Min Act: -0.1700
Data Index: 3343276 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19