Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 109 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2690. Min Act: -0.0001

Data Index: 1100254 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2409. Min Act: -0.0001

Data Index: 858809 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1121816 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2573. Min Act: -0.0001

Data Index: 399084 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1223804 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1207854 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1037397 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2301. Min Act: -0.0001

Data Index: 303307 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2430. Min Act: -0.0001

Data Index: 174910 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2273. Min Act: -0.0001

Data Index: 728649 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1327123 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2109. Min Act: -0.0001

Data Index: 1342670 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2082. Min Act: -0.0001

Data Index: 635146 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2213. Min Act: -0.0001

Data Index: 380423 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1974. Min Act: -0.0001

Data Index: 310455 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2407. Min Act: -0.0001

Data Index: 556134 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2355. Min Act: -0.0001

Data Index: 804406 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1262783 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1131593 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2043. Min Act: -0.0001

Data Index: 525448 (C4 (Web Text))

Max Activating Token Index: 157