Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 877 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')
Text #0
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0296. Min Act: -0.0001
Data Index: 640300 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0288. Min Act: -0.0002
Data Index: 442316 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0284. Min Act: -0.0001
Data Index: 481119 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0269. Min Act: -0.0001
Data Index: 1315717 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0274. Min Act: -0.0001
Data Index: 434511 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0275. Min Act: -0.0001
Data Index: 995653 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0272. Min Act: -0.0001
Data Index: 755380 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0265. Min Act: -0.0001
Data Index: 909555 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0258. Min Act: -0.0001
Data Index: 794331 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0253. Min Act: -0.0001
Data Index: 76292 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0252. Min Act: -0.0001
Data Index: 724840 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0239. Min Act: -0.0001
Data Index: 1629119 (Python Code)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0246. Min Act: -0.0001
Data Index: 401322 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0252. Min Act: -0.0001
Data Index: 681732 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0235. Min Act: -0.0001
Data Index: 1148671 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0239. Min Act: -0.0001
Data Index: 53683 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0243. Min Act: -0.0001
Data Index: 400454 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0239. Min Act: -0.0001
Data Index: 646582 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0232. Min Act: -0.0001
Data Index: 879152 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0296. Min Range: -0.0296
Max Act: 0.0234. Min Act: -0.0001
Data Index: 1380374 (Python Code)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19