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

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

Neuron 68 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.6682. Min Act: -0.0000

Data Index: 406515 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1338099 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1084833 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5394. Min Act: -0.0000

Data Index: 566818 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5152. Min Act: -0.0000

Data Index: 471566 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5178. Min Act: -0.0000

Data Index: 981055 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5359. Min Act: -0.0000

Data Index: 951277 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1258307 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1584939 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1507706 (Python Code)

Max Activating Token Index: 63

Text #10

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1438795 (Python Code)

Max Activating Token Index: 989

Text #11

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1018318 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4804. Min Act: -0.0000

Data Index: 348937 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4604. Min Act: -0.0000

Data Index: 4476 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1427670 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1585911 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1285839 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1159755 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4950. Min Act: -0.0000

Data Index: 855393 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1513492 (Python Code)

Max Activating Token Index: 7