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

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

Neuron 1377 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0000

Data Index: 218324 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0445. Min Act: -0.0000

Data Index: 677450 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0406. Min Act: -0.0000

Data Index: 8440 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1313273 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1234025 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0355. Min Act: -0.0000

Data Index: 339697 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0349. Min Act: -0.0000

Data Index: 266586 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0327. Min Act: -0.0000

Data Index: 629337 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1007540 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0334. Min Act: -0.0000

Data Index: 605374 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0340. Min Act: -0.0000

Data Index: 186670 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0309. Min Act: -0.0000

Data Index: 417853 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0298. Min Act: -0.0000

Data Index: 1006591 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0305. Min Act: -0.0000

Data Index: 708356 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0328. Min Act: -0.0000

Data Index: 1271996 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0281. Min Act: -0.0000

Data Index: 174211 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0286. Min Act: -0.0000

Data Index: 603783 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0324. Min Act: -0.0000

Data Index: 58355 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0300. Min Act: -0.0000

Data Index: 773032 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0277. Min Act: -0.0000

Data Index: 205798 (C4 (Web Text))

Max Activating Token Index: 807