Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2328 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.3972. Min Range: -2.3972
Max Act: 2.3972. Min Act: 0.0000
Data Index: 1431945 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3972. Min Range: -2.3972
Max Act: 2.1540. Min Act: -0.0000
Data Index: 728519 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.8555. Min Act: -0.0000
Data Index: 1618286 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.7432. Min Act: 0.0000
Data Index: 1870961 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.7632. Min Act: -0.0000
Data Index: 1399448 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.6543. Min Act: -0.0000
Data Index: 1605519 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.6521. Min Act: -0.0000
Data Index: 1566902 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.6175. Min Act: 0.0001
Data Index: 845350 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.5253. Min Act: -0.0000
Data Index: 1910779 (The Pile)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.6187. Min Act: -0.0000
Data Index: 1963018 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.4627. Min Act: -0.0000
Data Index: 756433 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.5412. Min Act: -0.0000
Data Index: 313741 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.5132. Min Act: -0.0000
Data Index: 1496604 (The Pile)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.4222. Min Act: 0.0001
Data Index: 411990 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.5132. Min Act: 0.0000
Data Index: 1187879 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.5124. Min Act: -0.0000
Data Index: 339007 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.4911. Min Act: -0.0000
Data Index: 900691 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.5936. Min Act: -0.0000
Data Index: 1782308 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.3988. Min Act: 0.0000
Data Index: 1015125 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3972. Min Range: -2.3972
Max Act: 1.4555. Min Act: 0.0001
Data Index: 729503 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19