Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3669 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.5220. Min Act: -0.1700
Data Index: 1399605 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.4594. Min Act: -0.1700
Data Index: 1605324 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.4280. Min Act: -0.1700
Data Index: 1230096 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3967. Min Act: -0.1700
Data Index: 6428651 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3967. Min Act: -0.1700
Data Index: 3522231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 615871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 4094570 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 2157527 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 8349046 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 8006079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 7811046 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 3499051 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 7526201 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 6667295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 6615897 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 6046943 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3653. Min Act: -0.1700
Data Index: 5203408 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3340. Min Act: -0.1700
Data Index: 115828 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3340. Min Act: -0.1700
Data Index: 2217450 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5220. Min Range: -3.5220
Max Act: 3.3340. Min Act: -0.1700
Data Index: 4111732 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19