Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2958 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0511. Min Act: -0.0001
Data Index: 240297 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0321. Min Act: -0.0001
Data Index: 1282281 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0348. Min Act: -0.0001
Data Index: 182845 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0274. Min Act: -0.0001
Data Index: 758842 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0359. Min Act: -0.0001
Data Index: 950984 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0283. Min Act: -0.0001
Data Index: 1277407 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0315. Min Act: -0.0001
Data Index: 216502 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0362. Min Act: -0.0001
Data Index: 1312946 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0310. Min Act: -0.0001
Data Index: 731375 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0354. Min Act: -0.0001
Data Index: 737969 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0349. Min Act: -0.0001
Data Index: 908663 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0312. Min Act: -0.0001
Data Index: 1210646 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0301. Min Act: -0.0001
Data Index: 1128915 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0318. Min Act: -0.0001
Data Index: 1332986 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0303. Min Act: -0.0001
Data Index: 818982 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0316. Min Act: -0.0001
Data Index: 1115935 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0281. Min Act: -0.0001
Data Index: 578324 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0326. Min Act: -0.0001
Data Index: 552797 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0292. Min Act: -0.0001
Data Index: 396831 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0511. Min Range: -0.0511
Max Act: 0.0255. Min Act: -0.0001
Data Index: 136115 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19