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

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

Neuron 2938 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1224699 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2671. Min Act: -0.0000

Data Index: 982086 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1300136 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2467. Min Act: -0.0000

Data Index: 60452 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1036983 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2442. Min Act: -0.0000

Data Index: 289551 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2275. Min Act: -0.0000

Data Index: 588428 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.1890. Min Act: -0.0000

Data Index: 708649 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2094. Min Act: -0.0000

Data Index: 999995 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2118. Min Act: -0.0000

Data Index: 754831 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2043. Min Act: -0.0000

Data Index: 636948 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2067. Min Act: -0.0000

Data Index: 106926 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2146. Min Act: -0.0000

Data Index: 17614 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2107. Min Act: -0.0000

Data Index: 301977 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.1905. Min Act: -0.0000

Data Index: 827436 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2115. Min Act: -0.0000

Data Index: 861003 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1182013 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.1948. Min Act: -0.0000

Data Index: 417059 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.2009. Min Act: -0.0000

Data Index: 676091 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.1947. Min Act: -0.0000

Data Index: 863621 (C4 (Web Text))

Max Activating Token Index: 114