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

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

Neuron 5850 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: 1.0270. Min Range: -1.0270

Max Act: 1.0270. Min Act: -0.0000

Data Index: 600033 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9741. Min Act: -0.0000

Data Index: 360061 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9842. Min Act: 0.0000

Data Index: 1441270 (Python Code)

Max Activating Token Index: 1011

Text #3

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9712. Min Act: -0.0000

Data Index: 283170 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0253. Min Act: -0.0000

Data Index: 746415 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7703. Min Act: -0.0000

Data Index: 1305526 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1437370 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1656927 (Python Code)

Max Activating Token Index: 885

Text #8

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1158542 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6943. Min Act: -0.0000

Data Index: 383265 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1258047 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1624686 (Python Code)

Max Activating Token Index: 624

Text #12

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7234. Min Act: 0.0000

Data Index: 1085548 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7086. Min Act: -0.0000

Data Index: 352791 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1546160 (Python Code)

Max Activating Token Index: 908

Text #15

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6812. Min Act: 0.0000

Data Index: 1387381 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1540510 (Python Code)

Max Activating Token Index: 977

Text #17

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1578073 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6610. Min Act: 0.0000

Data Index: 1521007 (Python Code)

Max Activating Token Index: 905

Text #19

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1460883 (Python Code)

Max Activating Token Index: 1003