Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2033 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.7195. Min Act: -0.0001
Data Index: 1212383 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.5737. Min Act: -0.0001
Data Index: 1167236 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.3795. Min Act: -0.0001
Data Index: 578240 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.3390. Min Act: -0.0001
Data Index: 418608 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.4468. Min Act: -0.0001
Data Index: 27489 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.1985. Min Act: -0.0001
Data Index: 1294180 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.1752. Min Act: -0.0001
Data Index: 735679 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.0692. Min Act: -0.0001
Data Index: 1099736 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.1830. Min Act: -0.0001
Data Index: 1080096 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.2949. Min Act: -0.0001
Data Index: 545513 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.1327. Min Act: -0.0001
Data Index: 664407 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.1133. Min Act: -0.0001
Data Index: 1324771 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7195. Min Range: -2.7195
Max Act: 1.9785. Min Act: -0.0001
Data Index: 1243689 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.0814. Min Act: -0.0001
Data Index: 1258365 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.0747. Min Act: -0.0001
Data Index: 383908 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.0679. Min Act: -0.0001
Data Index: 626395 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7195. Min Range: -2.7195
Max Act: 1.9465. Min Act: -0.0001
Data Index: 230231 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.0228. Min Act: -0.0001
Data Index: 761657 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7195. Min Range: -2.7195
Max Act: 2.0009. Min Act: -0.0001
Data Index: 507974 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7195. Min Range: -2.7195
Max Act: 1.8942. Min Act: -0.0001
Data Index: 374799 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19