Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2919 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0629. Min Act: -0.0001
Data Index: 257586 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0613. Min Act: -0.0001
Data Index: 89324 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0524. Min Act: -0.0001
Data Index: 289134 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0481. Min Act: -0.0001
Data Index: 1313647 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0441. Min Act: -0.0001
Data Index: 269870 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0425. Min Act: -0.0001
Data Index: 1090354 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0403. Min Act: -0.0001
Data Index: 1158799 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0376. Min Act: -0.0001
Data Index: 221327 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0340. Min Act: -0.0001
Data Index: 1127811 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0340. Min Act: -0.0001
Data Index: 1290378 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0320. Min Act: -0.0001
Data Index: 1195200 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0322. Min Act: -0.0001
Data Index: 910497 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0316. Min Act: -0.0001
Data Index: 146391 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0315. Min Act: -0.0001
Data Index: 729837 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0322. Min Act: -0.0001
Data Index: 599356 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0320. Min Act: -0.0001
Data Index: 1057004 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0277. Min Act: -0.0001
Data Index: 721598 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0299. Min Act: -0.0001
Data Index: 1188101 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0281. Min Act: -0.0001
Data Index: 495321 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0629. Min Range: -0.0629
Max Act: 0.0290. Min Act: -0.0001
Data Index: 288488 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19