Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4652 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.6304. Min Act: -0.1700
Data Index: 5609820 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.5054. Min Act: -0.1700
Data Index: 529477 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.4429. Min Act: -0.1700
Data Index: 2151482 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.4429. Min Act: -0.1700
Data Index: 2863013 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.4117. Min Act: -0.1700
Data Index: 1870247 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3804. Min Act: -0.1700
Data Index: 7215744 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.4117. Min Act: -0.1700
Data Index: 4632505 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.4117. Min Act: -0.1700
Data Index: 4620131 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3804. Min Act: -0.1700
Data Index: 8576871 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3492. Min Act: -0.1700
Data Index: 3812144 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3492. Min Act: -0.1700
Data Index: 426232 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3492. Min Act: -0.1700
Data Index: 4749628 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3492. Min Act: -0.1700
Data Index: 6172542 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3804. Min Act: -0.1700
Data Index: 2565580 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3492. Min Act: -0.1700
Data Index: 4160307 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3179. Min Act: -0.1700
Data Index: 5866489 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3179. Min Act: -0.1700
Data Index: 2067138 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3179. Min Act: -0.1700
Data Index: 5044708 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3179. Min Act: -0.1700
Data Index: 3616611 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6304. Min Range: -5.6304
Max Act: 5.3492. Min Act: -0.1700
Data Index: 3830581 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19