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

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

Neuron 4333 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: 0.7234. Min Range: -0.7234

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1320157 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.7234. Min Act: -0.0000

Data Index: 212848 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1200858 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6642. Min Act: -0.0000

Data Index: 703622 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5835. Min Act: -0.0000

Data Index: 611692 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1602519 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1165287 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5607. Min Act: -0.0000

Data Index: 880090 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1644561 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1169914 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1484801 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4827. Min Act: -0.0000

Data Index: 164054 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1606601 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1423027 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5005. Min Act: -0.0000

Data Index: 404208 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4924. Min Act: -0.0000

Data Index: 287225 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4704. Min Act: -0.0000

Data Index: 478454 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4806. Min Act: -0.0000

Data Index: 826714 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1597740 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1411941 (Python Code)

Max Activating Token Index: 965