Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1823 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.6063. Min Act: -0.0001
Data Index: 494242 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.5730. Min Act: -0.0001
Data Index: 1357172 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.5713. Min Act: -0.0001
Data Index: 1321458 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.5392. Min Act: -0.0001
Data Index: 975093 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.5513. Min Act: -0.0001
Data Index: 13210 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4928. Min Act: -0.0001
Data Index: 470276 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.5139. Min Act: -0.0001
Data Index: 629127 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.5099. Min Act: -0.0001
Data Index: 50058 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.5173. Min Act: -0.0001
Data Index: 977920 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4584. Min Act: -0.0001
Data Index: 642233 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4724. Min Act: -0.0001
Data Index: 702648 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4844. Min Act: -0.0001
Data Index: 521590 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4976. Min Act: -0.0001
Data Index: 686029 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4795. Min Act: -0.0001
Data Index: 244749 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4757. Min Act: -0.0001
Data Index: 10810 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4728. Min Act: -0.0001
Data Index: 1065305 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4423. Min Act: -0.0001
Data Index: 1170215 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4652. Min Act: -0.0001
Data Index: 833477 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4615. Min Act: -0.0001
Data Index: 64092 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6063. Min Range: -0.6063
Max Act: 0.4799. Min Act: -0.0001
Data Index: 745640 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19