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

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

Neuron 4049 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: 0.8932. Min Range: -0.8932

Max Act: 0.8932. Min Act: 0.0001

Data Index: 400955 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8854. Min Act: 0.0001

Data Index: 1034946 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7638. Min Act: -0.0000

Data Index: 427633 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7824. Min Act: 0.0000

Data Index: 921926 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7874. Min Act: 0.0000

Data Index: 1159663 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7597. Min Act: -0.0000

Data Index: 146862 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7298. Min Act: 0.0000

Data Index: 50695 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7465. Min Act: 0.0000

Data Index: 104237 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7599. Min Act: 0.0000

Data Index: 1341191 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7296. Min Act: -0.0000

Data Index: 600294 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6900. Min Act: 0.0000

Data Index: 56574 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6456. Min Act: 0.0001

Data Index: 146321 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6706. Min Act: -0.0000

Data Index: 3876 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6308. Min Act: 0.0000

Data Index: 874540 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6401. Min Act: 0.0000

Data Index: 612049 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6762. Min Act: 0.0000

Data Index: 1261142 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6576. Min Act: 0.0000

Data Index: 146130 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6253. Min Act: 0.0001

Data Index: 1205287 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6404. Min Act: 0.0001

Data Index: 813609 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6207. Min Act: 0.0000

Data Index: 189445 (C4 (Web Text))

Max Activating Token Index: 255