Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1258 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.8563. Min Act: -0.0001
Data Index: 767266 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.8241. Min Act: -0.0001
Data Index: 406307 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.7460. Min Act: -0.0001
Data Index: 149350 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.6492. Min Act: -0.0001
Data Index: 356117 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.6382. Min Act: -0.0001
Data Index: 578946 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.6446. Min Act: -0.0001
Data Index: 126155 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5971. Min Act: -0.0001
Data Index: 347708 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5989. Min Act: -0.0001
Data Index: 165173 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.6167. Min Act: -0.0001
Data Index: 52315 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5771. Min Act: -0.0001
Data Index: 595538 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5684. Min Act: -0.0001
Data Index: 204091 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5544. Min Act: -0.0001
Data Index: 940496 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5922. Min Act: -0.0001
Data Index: 774105 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5577. Min Act: -0.0001
Data Index: 88973 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5488. Min Act: -0.0001
Data Index: 514987 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5586. Min Act: -0.0001
Data Index: 198060 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5608. Min Act: -0.0001
Data Index: 512348 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5387. Min Act: -0.0001
Data Index: 230232 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5555. Min Act: -0.0001
Data Index: 212209 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8563. Min Range: -0.8563
Max Act: 0.5316. Min Act: -0.0001
Data Index: 1328345 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19