Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2975 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.2725. Min Act: -0.0000
Data Index: 1037488 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.0169. Min Act: -0.0000
Data Index: 691674 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.0686. Min Act: -0.0000
Data Index: 168267 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9125. Min Act: -0.0000
Data Index: 1066098 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.7188. Min Act: -0.0000
Data Index: 1333072 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.8463. Min Act: -0.0000
Data Index: 827522 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9904. Min Act: -0.0000
Data Index: 1921744 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.8673. Min Act: -0.0000
Data Index: 29558 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.8692. Min Act: -0.0000
Data Index: 868454 (The Pile)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.8674. Min Act: -0.0000
Data Index: 1007232 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.5997. Min Act: -0.0000
Data Index: 1855965 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.7497. Min Act: -0.0000
Data Index: 1937108 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.6426. Min Act: -0.0000
Data Index: 89400 (The Pile)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.6280. Min Act: -0.0000
Data Index: 1651468 (The Pile)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.6197. Min Act: -0.0000
Data Index: 58959 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.5641. Min Act: -0.0000
Data Index: 1885101 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.4190. Min Act: -0.0000
Data Index: 258021 (The Pile)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.3946. Min Act: -0.0000
Data Index: 454258 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.5437. Min Act: -0.0000
Data Index: 1337711 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.5538. Min Act: -0.0000
Data Index: 1968101 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19