Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2783 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0457. Min Act: -0.0001
Data Index: 1445891 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0310. Min Act: -0.0001
Data Index: 1612151 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0310. Min Act: -0.0001
Data Index: 1184171 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0287. Min Act: -0.0001
Data Index: 969436 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0285. Min Act: -0.0001
Data Index: 970835 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0284. Min Act: -0.0001
Data Index: 1499215 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0293. Min Act: -0.0001
Data Index: 1371229 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0239. Min Act: -0.0001
Data Index: 679692 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0230. Min Act: -0.0001
Data Index: 553117 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0225. Min Act: -0.0001
Data Index: 1268385 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0225. Min Act: -0.0001
Data Index: 1448586 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0221. Min Act: -0.0001
Data Index: 1836507 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0220. Min Act: -0.0001
Data Index: 1413246 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0215. Min Act: -0.0001
Data Index: 1189296 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0215. Min Act: -0.0001
Data Index: 1288380 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0211. Min Act: -0.0001
Data Index: 1872358 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0208. Min Act: -0.0001
Data Index: 879930 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0211. Min Act: -0.0001
Data Index: 190554 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0198. Min Act: -0.0001
Data Index: 209956 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0457. Min Range: -0.0457
Max Act: 0.0198. Min Act: -0.0001
Data Index: 1587532 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19