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

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

Neuron 4744 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.9340. Min Act: -0.0000

Data Index: 158709 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.7850. Min Act: -0.0000

Data Index: 1285710 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.8269. Min Act: -0.0000

Data Index: 566675 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.8140. Min Act: -0.0000

Data Index: 1158848 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.8085. Min Act: -0.0000

Data Index: 1030444 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.6773. Min Act: -0.0000

Data Index: 102390 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.7721. Min Act: -0.0000

Data Index: 956040 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.7500. Min Act: -0.0000

Data Index: 760724 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.6418. Min Act: -0.0000

Data Index: 1144114 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.7277. Min Act: -0.0000

Data Index: 437066 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.6143. Min Act: -0.0000

Data Index: 403765 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.6228. Min Act: -0.0000

Data Index: 1101206 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.6912. Min Act: -0.0000

Data Index: 249375 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.6857. Min Act: -0.0000

Data Index: 155000 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.5791. Min Act: -0.0000

Data Index: 879593 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.6666. Min Act: -0.0000

Data Index: 860172 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.5418. Min Act: -0.0000

Data Index: 828711 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.6422. Min Act: -0.0000

Data Index: 744781 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.6297. Min Act: -0.0000

Data Index: 679983 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.9340. Min Range: -1.9340

Max Act: 1.6187. Min Act: -0.0000

Data Index: 602852 (C4 (Web Text))

Max Activating Token Index: 26