Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2841 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.7321. Min Act: -0.0000

Data Index: 661053 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.7667. Min Act: -0.0000

Data Index: 792584 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.7941. Min Act: -0.0000

Data Index: 978032 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.5545. Min Act: -0.0000

Data Index: 793894 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.6422. Min Act: -0.0000

Data Index: 382192 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.5500. Min Act: -0.0000

Data Index: 520380 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1356114 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.5876. Min Act: -0.0000

Data Index: 1437581 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.4870. Min Act: -0.0000

Data Index: 53534 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.3612. Min Act: -0.0000

Data Index: 1505009 (Python Code)

Max Activating Token Index: 175

Text #10

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.3805. Min Act: -0.0000

Data Index: 528312 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.4043. Min Act: -0.0000

Data Index: 77099 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.3238. Min Act: -0.0000

Data Index: 541578 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.4077. Min Act: -0.0000

Data Index: 964817 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.4021. Min Act: -0.0000

Data Index: 1033868 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1055888 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.3424. Min Act: -0.0000

Data Index: 568758 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.2677. Min Act: -0.0000

Data Index: 440892 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1623031 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 1.7941. Min Range: -1.7941

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1203001 (C4 (Web Text))

Max Activating Token Index: 1009