Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2683 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0289. Min Act: -0.0001
Data Index: 259192 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0251. Min Act: -0.0001
Data Index: 259116 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0240. Min Act: -0.0001
Data Index: 1094506 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0236. Min Act: -0.0001
Data Index: 273356 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0231. Min Act: -0.0001
Data Index: 16173 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0227. Min Act: -0.0001
Data Index: 484418 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0234. Min Act: -0.0001
Data Index: 1495084 (Python Code)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0210. Min Act: -0.0001
Data Index: 176611 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0201. Min Act: -0.0001
Data Index: 169720 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0212. Min Act: -0.0001
Data Index: 1378809 (Python Code)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0207. Min Act: -0.0001
Data Index: 7798 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0213. Min Act: -0.0001
Data Index: 348257 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0198. Min Act: -0.0001
Data Index: 323227 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0204. Min Act: -0.0001
Data Index: 1330975 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0203. Min Act: -0.0001
Data Index: 1615862 (Python Code)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0207. Min Act: -0.0001
Data Index: 1614938 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0202. Min Act: -0.0001
Data Index: 55340 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0200. Min Act: -0.0001
Data Index: 250413 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0201. Min Act: -0.0001
Data Index: 390199 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0289. Min Range: -0.0289
Max Act: 0.0200. Min Act: -0.0001
Data Index: 1403140 (Python Code)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19