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

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

Neuron 856 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: 3.5035. Min Range: -3.5035

Max Act: 3.5035. Min Act: -0.0000

Data Index: 634296 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.4001. Min Act: -0.0000

Data Index: 536085 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 3.5035. Min Range: -3.5035

Max Act: 2.3207. Min Act: -0.0000

Data Index: 267575 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 3.5035. Min Range: -3.5035

Max Act: 2.4179. Min Act: -0.0000

Data Index: 1195394 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 3.5035. Min Range: -3.5035

Max Act: 2.4011. Min Act: -0.0000

Data Index: 772510 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 3.5035. Min Range: -3.5035

Max Act: 2.2311. Min Act: -0.0000

Data Index: 385728 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 3.5035. Min Range: -3.5035

Max Act: 2.3139. Min Act: -0.0000

Data Index: 138389 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 3.5035. Min Range: -3.5035

Max Act: 2.1818. Min Act: -0.0000

Data Index: 1295846 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 3.5035. Min Range: -3.5035

Max Act: 2.0367. Min Act: -0.0000

Data Index: 665023 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.9306. Min Act: -0.0000

Data Index: 1301323 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.9234. Min Act: -0.0000

Data Index: 189303 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.9117. Min Act: -0.0000

Data Index: 900506 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.7715. Min Act: -0.0000

Data Index: 115677 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.9693. Min Act: -0.0000

Data Index: 239985 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.8473. Min Act: -0.0000

Data Index: 916023 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.8406. Min Act: -0.0000

Data Index: 1068146 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.8459. Min Act: -0.0000

Data Index: 1337560 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.8125. Min Act: -0.0000

Data Index: 1169876 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.8404. Min Act: -0.0000

Data Index: 1344865 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 3.5035. Min Range: -3.5035

Max Act: 1.7925. Min Act: -0.0000

Data Index: 533993 (C4 (Web Text))

Max Activating Token Index: 364