Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1453 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 3.3269. Min Range: -3.3269
Max Act: 3.3269. Min Act: -0.0001
Data Index: 1994021 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.8064. Min Act: -0.0001
Data Index: 783708 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.5701. Min Act: -0.0001
Data Index: 877174 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.5677. Min Act: -0.0001
Data Index: 1670482 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.1720. Min Act: -0.0001
Data Index: 682013 (The Pile)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.0069. Min Act: -0.0001
Data Index: 1188980 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.2374. Min Act: -0.0001
Data Index: 1063115 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.3154. Min Act: -0.0001
Data Index: 672173 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.0304. Min Act: -0.0001
Data Index: 1409282 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.0334. Min Act: -0.0001
Data Index: 465112 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3269. Min Range: -3.3269
Max Act: 1.8686. Min Act: -0.0001
Data Index: 1645363 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3269. Min Range: -3.3269
Max Act: 1.9933. Min Act: -0.0001
Data Index: 1898445 (The Pile)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3269. Min Range: -3.3269
Max Act: 1.9222. Min Act: -0.0001
Data Index: 1674773 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.0231. Min Act: -0.0001
Data Index: 1320645 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3269. Min Range: -3.3269
Max Act: 1.9083. Min Act: -0.0001
Data Index: 1314443 (The Pile)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.1577. Min Act: -0.0001
Data Index: 830368 (The Pile)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3269. Min Range: -3.3269
Max Act: 2.0004. Min Act: -0.0001
Data Index: 913427 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3269. Min Range: -3.3269
Max Act: 1.8074. Min Act: -0.0001
Data Index: 93665 (The Pile)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3269. Min Range: -3.3269
Max Act: 1.8102. Min Act: -0.0001
Data Index: 83973 (The Pile)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3269. Min Range: -3.3269
Max Act: 1.9793. Min Act: -0.0001
Data Index: 1187632 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19