Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1492 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.1360. Min Range: -2.1360
Max Act: 2.1360. Min Act: -0.0001
Data Index: 132667 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.9657. Min Act: -0.0001
Data Index: 342827 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.8255. Min Act: -0.0001
Data Index: 246505 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.7247. Min Act: -0.0001
Data Index: 1056583 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.7215. Min Act: -0.0001
Data Index: 1354708 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.6194. Min Act: -0.0001
Data Index: 930557 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.7144. Min Act: -0.0001
Data Index: 299003 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.7891. Min Act: -0.0001
Data Index: 670865 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.5791. Min Act: -0.0001
Data Index: 1329562 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.5356. Min Act: -0.0001
Data Index: 638885 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.6327. Min Act: -0.0001
Data Index: 1141923 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.5905. Min Act: -0.0001
Data Index: 1195666 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.5735. Min Act: -0.0001
Data Index: 817763 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.5666. Min Act: -0.0001
Data Index: 928217 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.5369. Min Act: -0.0001
Data Index: 419432 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.6180. Min Act: -0.0001
Data Index: 1159201 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.5214. Min Act: -0.0001
Data Index: 210757 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.4279. Min Act: -0.0001
Data Index: 874223 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.5947. Min Act: -0.0001
Data Index: 777082 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1360. Min Range: -2.1360
Max Act: 1.5957. Min Act: -0.0001
Data Index: 595741 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19