Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 42 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.9230. Min Act: -0.0001
Data Index: 420400 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7844. Min Act: -0.0001
Data Index: 1181857 (The Pile)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.8031. Min Act: -0.0001
Data Index: 1565292 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7514. Min Act: -0.0001
Data Index: 1433601 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.8166. Min Act: -0.0001
Data Index: 550865 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7505. Min Act: -0.0001
Data Index: 63845 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7629. Min Act: -0.0001
Data Index: 598904 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7492. Min Act: -0.0001
Data Index: 36841 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7967. Min Act: -0.0001
Data Index: 1258717 (The Pile)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7248. Min Act: -0.0001
Data Index: 1173918 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7720. Min Act: -0.0001
Data Index: 1688226 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7181. Min Act: -0.0001
Data Index: 430808 (The Pile)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7355. Min Act: -0.0001
Data Index: 1756831 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7267. Min Act: -0.0001
Data Index: 1416246 (The Pile)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7952. Min Act: -0.0001
Data Index: 372946 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7707. Min Act: -0.0001
Data Index: 1119881 (The Pile)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7140. Min Act: -0.0001
Data Index: 885793 (The Pile)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.7302. Min Act: -0.0001
Data Index: 1000901 (The Pile)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.6329. Min Act: -0.0001
Data Index: 880594 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9230. Min Range: -0.9230
Max Act: 0.6986. Min Act: -0.0001
Data Index: 1580721 (The Pile)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19