Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4478 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0385. Min Act: -0.0001
Data Index: 194662 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0349. Min Act: -0.0001
Data Index: 122084 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0354. Min Act: -0.0001
Data Index: 1022910 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0310. Min Act: -0.0001
Data Index: 1028471 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0299. Min Act: -0.0001
Data Index: 530450 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0324. Min Act: -0.0001
Data Index: 1053020 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0291. Min Act: -0.0001
Data Index: 953950 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0322. Min Act: -0.0001
Data Index: 995923 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0304. Min Act: -0.0001
Data Index: 1153488 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0302. Min Act: -0.0001
Data Index: 168466 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0282. Min Act: -0.0001
Data Index: 926266 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0293. Min Act: -0.0001
Data Index: 1535121 (Python Code)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0292. Min Act: -0.0001
Data Index: 974958 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0301. Min Act: -0.0001
Data Index: 1235791 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0309. Min Act: -0.0001
Data Index: 1338885 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0314. Min Act: -0.0001
Data Index: 1063565 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0276. Min Act: -0.0001
Data Index: 1123029 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0270. Min Act: -0.0001
Data Index: 1383203 (Python Code)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0308. Min Act: -0.0001
Data Index: 136210 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0385. Min Range: -0.0385
Max Act: 0.0255. Min Act: -0.0001
Data Index: 425711 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19