Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2416 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1658. Min Act: -0.0001
Data Index: 1625285 (Python Code)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1417. Min Act: -0.0001
Data Index: 1619335 (Python Code)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1263. Min Act: -0.0001
Data Index: 1624959 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1313. Min Act: -0.0001
Data Index: 1581318 (Python Code)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1272. Min Act: -0.0001
Data Index: 1390949 (Python Code)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1275. Min Act: -0.0001
Data Index: 1362897 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1179. Min Act: -0.0001
Data Index: 1394566 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1200. Min Act: -0.0001
Data Index: 1433985 (Python Code)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1230. Min Act: -0.0001
Data Index: 1452137 (Python Code)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1275. Min Act: -0.0001
Data Index: 1446064 (Python Code)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1237. Min Act: -0.0001
Data Index: 1567730 (Python Code)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1227. Min Act: -0.0001
Data Index: 1601940 (Python Code)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1261. Min Act: -0.0001
Data Index: 1643929 (Python Code)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1167. Min Act: -0.0001
Data Index: 1418738 (Python Code)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1213. Min Act: -0.0001
Data Index: 1525162 (Python Code)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1156. Min Act: -0.0001
Data Index: 1585077 (Python Code)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1194. Min Act: -0.0001
Data Index: 1414187 (Python Code)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1080. Min Act: -0.0001
Data Index: 1516841 (Python Code)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1226. Min Act: -0.0001
Data Index: 1528975 (Python Code)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1658. Min Range: -0.1658
Max Act: 0.1184. Min Act: -0.0001
Data Index: 1652443 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19