Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2819 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.4252. Min Act: -0.0001
Data Index: 271242 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.3227. Min Act: -0.0000
Data Index: 1266090 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4252. Min Range: -2.4252
Max Act: 1.9963. Min Act: -0.0001
Data Index: 857022 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.1503. Min Act: -0.0001
Data Index: 444368 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.0315. Min Act: -0.0000
Data Index: 624113 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.0047. Min Act: -0.0000
Data Index: 975976 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.0141. Min Act: -0.0001
Data Index: 628198 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.1047. Min Act: -0.0001
Data Index: 214382 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4252. Min Range: -2.4252
Max Act: 1.9737. Min Act: -0.0000
Data Index: 98756 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4252. Min Range: -2.4252
Max Act: 1.8264. Min Act: -0.0001
Data Index: 170897 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.1283. Min Act: -0.0000
Data Index: 744461 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4252. Min Range: -2.4252
Max Act: 1.7279. Min Act: -0.0001
Data Index: 1359808 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.0254. Min Act: -0.0001
Data Index: 328243 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4252. Min Range: -2.4252
Max Act: 1.9075. Min Act: -0.0001
Data Index: 319884 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.1281. Min Act: -0.0000
Data Index: 57163 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.0975. Min Act: -0.0000
Data Index: 878501 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4252. Min Range: -2.4252
Max Act: 1.9859. Min Act: -0.0001
Data Index: 1219005 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4252. Min Range: -2.4252
Max Act: 1.8579. Min Act: -0.0001
Data Index: 548336 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4252. Min Range: -2.4252
Max Act: 2.0011. Min Act: -0.0001
Data Index: 191485 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4252. Min Range: -2.4252
Max Act: 1.9917. Min Act: -0.0001
Data Index: 904407 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19