Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 315 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.5567. Min Act: -0.0001
Data Index: 455552 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.2864. Min Act: -0.0001
Data Index: 1321475 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.2309. Min Act: -0.0001
Data Index: 1196036 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.3025. Min Act: -0.0001
Data Index: 822796 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.2973. Min Act: -0.0001
Data Index: 1315610 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.2162. Min Act: -0.0001
Data Index: 749558 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.2253. Min Act: -0.0001
Data Index: 1278751 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.1653. Min Act: -0.0001
Data Index: 1393228 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.0807. Min Act: -0.0001
Data Index: 1241759 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.1023. Min Act: -0.0001
Data Index: 587618 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.0880. Min Act: -0.0001
Data Index: 1338708 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.0793. Min Act: -0.0001
Data Index: 1572788 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.0360. Min Act: -0.0001
Data Index: 284318 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.0762. Min Act: -0.0001
Data Index: 102939 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.0404. Min Act: -0.0001
Data Index: 915392 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5567. Min Range: -1.5567
Max Act: 0.9976. Min Act: -0.0001
Data Index: 279674 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.0446. Min Act: -0.0001
Data Index: 1102646 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.0060. Min Act: -0.0001
Data Index: 727171 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.0019. Min Act: -0.0001
Data Index: 183553 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5567. Min Range: -1.5567
Max Act: 1.0235. Min Act: -0.0001
Data Index: 252835 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19