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

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

Neuron 5707 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: 2.0909. Min Range: -2.0909

Max Act: 2.0909. Min Act: -0.0000

Data Index: 1636133 (Python Code)

Max Activating Token Index: 373

Text #1

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.8218. Min Act: -0.0000

Data Index: 579266 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.8074. Min Act: -0.0000

Data Index: 416377 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.8377. Min Act: -0.0000

Data Index: 1451690 (Python Code)

Max Activating Token Index: 815

Text #4

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.7954. Min Act: -0.0000

Data Index: 705382 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.7887. Min Act: -0.0000

Data Index: 501446 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.7855. Min Act: -0.0000

Data Index: 1024979 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.7700. Min Act: -0.0000

Data Index: 885158 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.6684. Min Act: -0.0000

Data Index: 1614023 (Python Code)

Max Activating Token Index: 186

Text #9

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.8673. Min Act: -0.0000

Data Index: 914687 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.7507. Min Act: -0.0000

Data Index: 1645643 (Python Code)

Max Activating Token Index: 97

Text #11

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.6349. Min Act: -0.0000

Data Index: 218397 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.6426. Min Act: -0.0000

Data Index: 1532191 (Python Code)

Max Activating Token Index: 687

Text #13

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.6175. Min Act: -0.0000

Data Index: 1419663 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.7127. Min Act: -0.0000

Data Index: 1064014 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1488790 (Python Code)

Max Activating Token Index: 154

Text #16

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.5193. Min Act: -0.0000

Data Index: 1579401 (Python Code)

Max Activating Token Index: 329

Text #17

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.6602. Min Act: -0.0000

Data Index: 1621665 (Python Code)

Max Activating Token Index: 761

Text #18

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.6241. Min Act: -0.0000

Data Index: 1159048 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 2.0909. Min Range: -2.0909

Max Act: 1.7242. Min Act: -0.0000

Data Index: 1471904 (Python Code)

Max Activating Token Index: 446