Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3298 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1322. Min Act: -0.0001
Data Index: 963892 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1281. Min Act: -0.0001
Data Index: 497068 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1272. Min Act: -0.0001
Data Index: 1449236 (Python Code)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1276. Min Act: -0.0001
Data Index: 515913 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1271. Min Act: -0.0001
Data Index: 1130297 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1267. Min Act: -0.0001
Data Index: 1149674 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1342. Min Act: -0.0001
Data Index: 605214 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1314. Min Act: -0.0001
Data Index: 1231367 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1356. Min Act: -0.0001
Data Index: 872362 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1276. Min Act: -0.0001
Data Index: 90779 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1238. Min Act: -0.0001
Data Index: 1079698 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1223. Min Act: -0.0001
Data Index: 80168 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1268. Min Act: -0.0001
Data Index: 705209 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1270. Min Act: -0.0001
Data Index: 1528927 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1247. Min Act: -0.0001
Data Index: 862795 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1197. Min Act: -0.0001
Data Index: 104044 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1244. Min Act: -0.0001
Data Index: 1077248 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1233. Min Act: -0.0001
Data Index: 697515 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1224. Min Act: -0.0001
Data Index: 1304321 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1356. Min Range: -0.1356
Max Act: 0.1277. Min Act: -0.0001
Data Index: 133327 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19