Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1835 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7138. Min Range: -1.7138
Max Act: 1.7138. Min Act: -0.0001
Data Index: 827534 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7138. Min Range: -1.7138
Max Act: 1.1871. Min Act: -0.0001
Data Index: 398035 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7138. Min Range: -1.7138
Max Act: 1.1742. Min Act: -0.0001
Data Index: 1255582 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7138. Min Range: -1.7138
Max Act: 1.1090. Min Act: -0.0001
Data Index: 916454 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7138. Min Range: -1.7138
Max Act: 1.0725. Min Act: -0.0001
Data Index: 115420 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7138. Min Range: -1.7138
Max Act: 1.0726. Min Act: -0.0001
Data Index: 548464 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7138. Min Range: -1.7138
Max Act: 1.0459. Min Act: -0.0001
Data Index: 1060268 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.9391. Min Act: -0.0001
Data Index: 757738 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.9421. Min Act: -0.0001
Data Index: 828404 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.9281. Min Act: -0.0001
Data Index: 1112290 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.9120. Min Act: -0.0001
Data Index: 1188834 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.8788. Min Act: -0.0001
Data Index: 1218809 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.8895. Min Act: -0.0001
Data Index: 291619 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.8908. Min Act: -0.0001
Data Index: 549345 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.9176. Min Act: -0.0001
Data Index: 972555 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.8825. Min Act: -0.0001
Data Index: 529739 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.8630. Min Act: -0.0001
Data Index: 378845 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.9569. Min Act: -0.0001
Data Index: 515253 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.8897. Min Act: -0.0001
Data Index: 1314199 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7138. Min Range: -1.7138
Max Act: 0.8772. Min Act: -0.0001
Data Index: 1199732 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19