Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4492 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0353. Min Act: -0.0001
Data Index: 1233761 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0312. Min Act: -0.0001
Data Index: 516664 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0322. Min Act: -0.0001
Data Index: 1255837 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0269. Min Act: -0.0001
Data Index: 566977 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0258. Min Act: -0.0001
Data Index: 939797 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0274. Min Act: -0.0001
Data Index: 642344 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0278. Min Act: -0.0001
Data Index: 850054 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0241. Min Act: -0.0001
Data Index: 124725 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0247. Min Act: -0.0001
Data Index: 831088 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0236. Min Act: -0.0001
Data Index: 6670 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0273. Min Act: -0.0001
Data Index: 1237643 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0260. Min Act: -0.0001
Data Index: 503926 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0259. Min Act: -0.0001
Data Index: 1366134 (Python Code)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0296. Min Act: -0.0001
Data Index: 283831 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0281. Min Act: -0.0001
Data Index: 496003 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0253. Min Act: -0.0001
Data Index: 702212 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0262. Min Act: -0.0001
Data Index: 1281067 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0278. Min Act: -0.0001
Data Index: 1017196 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0251. Min Act: -0.0001
Data Index: 1626212 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0353. Min Range: -0.0353
Max Act: 0.0238. Min Act: -0.0001
Data Index: 1520219 (Python Code)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19