Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1217 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1462. Min Act: -0.0001
Data Index: 932145 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1321. Min Act: -0.0001
Data Index: 992270 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1364. Min Act: -0.0001
Data Index: 141659 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1472. Min Act: -0.0001
Data Index: 1552798 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1390. Min Act: -0.0001
Data Index: 559887 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1485. Min Act: -0.0001
Data Index: 21933 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1382. Min Act: -0.0001
Data Index: 1054948 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1285. Min Act: -0.0001
Data Index: 1147779 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1321. Min Act: -0.0001
Data Index: 91810 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1313. Min Act: -0.0001
Data Index: 863402 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1350. Min Act: -0.0001
Data Index: 935894 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1267. Min Act: -0.0001
Data Index: 200014 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1384. Min Act: -0.0001
Data Index: 365669 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1236. Min Act: -0.0001
Data Index: 99739 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1196. Min Act: -0.0001
Data Index: 125025 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1326. Min Act: -0.0001
Data Index: 1640737 (Python Code)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1282. Min Act: -0.0001
Data Index: 397151 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1315. Min Act: -0.0001
Data Index: 1032257 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1177. Min Act: -0.0001
Data Index: 1082092 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1485. Min Range: -0.1485
Max Act: 0.1367. Min Act: -0.0001
Data Index: 1333278 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19