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

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

Neuron 5662 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.1724. Min Act: 0.0001

Data Index: 1328441 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.0772. Min Act: -0.0000

Data Index: 920497 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.0589. Min Act: -0.0000

Data Index: 1089448 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.0350. Min Act: -0.0000

Data Index: 464292 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.0217. Min Act: -0.0000

Data Index: 237928 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.0276. Min Act: -0.0000

Data Index: 1248084 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9684. Min Act: -0.0000

Data Index: 998893 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.0053. Min Act: 0.0000

Data Index: 628985 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9577. Min Act: -0.0000

Data Index: 879612 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8931. Min Act: -0.0000

Data Index: 938597 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1068565 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9358. Min Act: -0.0000

Data Index: 294100 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8770. Min Act: -0.0000

Data Index: 347167 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9222. Min Act: -0.0000

Data Index: 954667 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9244. Min Act: -0.0000

Data Index: 518528 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8721. Min Act: -0.0000

Data Index: 210879 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1098994 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1271865 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1244804 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9105. Min Act: -0.0000

Data Index: 903574 (C4 (Web Text))

Max Activating Token Index: 441