Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 9 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0493. Min Act: -0.0001
Data Index: 1273971 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0457. Min Act: -0.0001
Data Index: 30993 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0410. Min Act: -0.0001
Data Index: 1056980 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0334. Min Act: -0.0001
Data Index: 885276 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0356. Min Act: -0.0001
Data Index: 126534 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0356. Min Act: -0.0001
Data Index: 1137326 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0337. Min Act: -0.0001
Data Index: 1179979 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0320. Min Act: -0.0001
Data Index: 1104531 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0309. Min Act: -0.0001
Data Index: 850467 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0289. Min Act: -0.0001
Data Index: 29378 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0302. Min Act: -0.0001
Data Index: 286535 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0315. Min Act: -0.0001
Data Index: 148928 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0383. Min Act: -0.0001
Data Index: 1106479 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0285. Min Act: -0.0001
Data Index: 1337981 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0304. Min Act: -0.0001
Data Index: 1639041 (Python Code)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0260. Min Act: -0.0001
Data Index: 768968 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0286. Min Act: -0.0001
Data Index: 753517 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0260. Min Act: -0.0001
Data Index: 705858 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0272. Min Act: -0.0001
Data Index: 31969 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0493. Min Range: -0.0493
Max Act: 0.0290. Min Act: -0.0001
Data Index: 956513 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19