Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 22 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7245. Min Range: -1.7245
Max Act: 1.7245. Min Act: -0.0000
Data Index: 957196 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7245. Min Range: -1.7245
Max Act: 1.5977. Min Act: -0.0000
Data Index: 455196 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7245. Min Range: -1.7245
Max Act: 1.4538. Min Act: -0.0000
Data Index: 277470 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7245. Min Range: -1.7245
Max Act: 1.2387. Min Act: -0.0000
Data Index: 202621 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.9923. Min Act: -0.0000
Data Index: 1321133 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.9586. Min Act: -0.0000
Data Index: 746796 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.8582. Min Act: -0.0000
Data Index: 994752 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.8016. Min Act: -0.0000
Data Index: 966123 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.7801. Min Act: -0.0000
Data Index: 231981 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.8039. Min Act: -0.0000
Data Index: 647669 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.7534. Min Act: -0.0000
Data Index: 602550 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.7903. Min Act: -0.0000
Data Index: 392085 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.8342. Min Act: -0.0000
Data Index: 975281 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.7514. Min Act: -0.0000
Data Index: 199336 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.7705. Min Act: -0.0000
Data Index: 540957 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.7450. Min Act: -0.0000
Data Index: 92763 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.7274. Min Act: -0.0000
Data Index: 955472 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.7077. Min Act: -0.0000
Data Index: 377420 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.7471. Min Act: -0.0000
Data Index: 782988 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7245. Min Range: -1.7245
Max Act: 0.7817. Min Act: -0.0000
Data Index: 318240 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19