Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2475 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9191. Min Range: -6.9191
Max Act: 6.9191. Min Act: -0.1700
Data Index: 8497173 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9191. Min Range: -6.9191
Max Act: 6.4191. Min Act: -0.1700
Data Index: 6520950 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9191. Min Range: -6.9191
Max Act: 6.2941. Min Act: -0.1700
Data Index: 6334325 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9191. Min Range: -6.9191
Max Act: 6.2316. Min Act: -0.1700
Data Index: 5910367 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9191. Min Range: -6.9191
Max Act: 6.1066. Min Act: -0.1700
Data Index: 8786139 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9191. Min Range: -6.9191
Max Act: 6.0753. Min Act: -0.1700
Data Index: 4823403 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9191. Min Range: -6.9191
Max Act: 6.0441. Min Act: -0.1700
Data Index: 4701679 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.9816. Min Act: -0.1700
Data Index: 8795802 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.9503. Min Act: -0.1700
Data Index: 80218 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.9503. Min Act: -0.1700
Data Index: 6869033 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.9503. Min Act: -0.1700
Data Index: 3969626 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.9503. Min Act: -0.1700
Data Index: 5186738 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.9191. Min Act: -0.1700
Data Index: 2439338 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.9191. Min Act: -0.1700
Data Index: 6653202 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.9191. Min Act: -0.1700
Data Index: 7050375 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.8878. Min Act: -0.1700
Data Index: 3554883 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.9191. Min Act: -0.1700
Data Index: 3415091 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.8878. Min Act: -0.1700
Data Index: 3715256 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.8878. Min Act: -0.1700
Data Index: 6608416 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9191. Min Range: -6.9191
Max Act: 5.8566. Min Act: -0.1700
Data Index: 4375457 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19