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

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

Neuron 5086 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.3201. Min Act: -0.0000

Data Index: 121180 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1302119 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2684. Min Act: -0.0000

Data Index: 647662 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2702. Min Act: -0.0000

Data Index: 65334 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2476. Min Act: -0.0000

Data Index: 223664 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2354. Min Act: -0.0000

Data Index: 534121 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2334. Min Act: -0.0000

Data Index: 490150 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2333. Min Act: -0.0000

Data Index: 368060 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2316. Min Act: -0.0000

Data Index: 465916 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2310. Min Act: -0.0000

Data Index: 735424 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2221. Min Act: -0.0000

Data Index: 657867 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1225617 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2112. Min Act: -0.0000

Data Index: 774142 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2082. Min Act: -0.0000

Data Index: 119869 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2061. Min Act: -0.0000

Data Index: 827296 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1220407 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.1983. Min Act: -0.0000

Data Index: 112616 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2050. Min Act: -0.0000

Data Index: 598904 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2092. Min Act: -0.0000

Data Index: 591179 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2011. Min Act: -0.0000

Data Index: 49842 (C4 (Web Text))

Max Activating Token Index: 328