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

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

Neuron 5866 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: 0.9010. Min Range: -0.9010

Max Act: 0.9010. Min Act: -0.0000

Data Index: 805475 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1234079 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8084. Min Act: -0.0000

Data Index: 413178 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1335691 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7937. Min Act: -0.0000

Data Index: 238346 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1165434 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7405. Min Act: -0.0000

Data Index: 944913 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7355. Min Act: -0.0000

Data Index: 635813 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1267229 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7325. Min Act: -0.0000

Data Index: 481874 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7203. Min Act: -0.0000

Data Index: 953504 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7318. Min Act: -0.0000

Data Index: 699208 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6543. Min Act: -0.0000

Data Index: 994681 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6555. Min Act: -0.0000

Data Index: 473300 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6259. Min Act: -0.0000

Data Index: 368763 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6680. Min Act: -0.0000

Data Index: 406044 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6518. Min Act: -0.0000

Data Index: 985551 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6380. Min Act: -0.0000

Data Index: 288599 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1228892 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6142. Min Act: -0.0000

Data Index: 212301 (C4 (Web Text))

Max Activating Token Index: 815