Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 639 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5504. Min Range: -9.5504
Max Act: 9.5504. Min Act: -0.1700
Data Index: 1220887 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5504. Min Range: -9.5504
Max Act: 9.2379. Min Act: -0.1700
Data Index: 6819540 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.9879. Min Act: -0.1700
Data Index: 4627660 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.9879. Min Act: -0.1700
Data Index: 144024 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.9254. Min Act: -0.1700
Data Index: 6510507 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.8629. Min Act: -0.1700
Data Index: 8472291 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.8004. Min Act: -0.1700
Data Index: 7733556 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.8004. Min Act: -0.1700
Data Index: 2355197 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.8004. Min Act: -0.1700
Data Index: 4909526 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.8004. Min Act: -0.1700
Data Index: 7228280 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.8004. Min Act: -0.1700
Data Index: 5088261 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.7379. Min Act: -0.1700
Data Index: 1740663 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.8004. Min Act: -0.1700
Data Index: 1711993 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.7379. Min Act: -0.1700
Data Index: 8441598 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.8004. Min Act: -0.1700
Data Index: 8118088 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.6754. Min Act: -0.1700
Data Index: 7365922 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.6754. Min Act: -0.1700
Data Index: 7680600 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.6754. Min Act: -0.1700
Data Index: 6379243 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.6129. Min Act: -0.1700
Data Index: 7050618 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5504. Min Range: -9.5504
Max Act: 8.6129. Min Act: -0.1700
Data Index: 8775381 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19