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

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

Neuron 4339 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8462. Min Range: -2.8462

Max Act: 2.8462. Min Act: -0.0000

Data Index: 998047 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.5146. Min Act: -0.0000

Data Index: 69066 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.4051. Min Act: -0.0000

Data Index: 216009 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.3159. Min Act: -0.0000

Data Index: 1181191 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.3625. Min Act: -0.0000

Data Index: 1196246 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.3120. Min Act: -0.0000

Data Index: 559262 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.3005. Min Act: -0.0000

Data Index: 985878 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.2948. Min Act: -0.0000

Data Index: 1043578 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.2940. Min Act: -0.0000

Data Index: 501834 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.2032. Min Act: -0.0000

Data Index: 1257443 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.2520. Min Act: -0.0000

Data Index: 213374 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.1785. Min Act: -0.0000

Data Index: 726619 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.2361. Min Act: -0.0000

Data Index: 186295 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.1588. Min Act: -0.0000

Data Index: 1023513 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1031995 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1321141 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1300324 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.2126. Min Act: -0.0000

Data Index: 575462 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.2897. Min Act: -0.0000

Data Index: 664286 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1231582 (C4 (Web Text))

Max Activating Token Index: 205