Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3606 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.2341. Min Act: -0.0003

Data Index: 1129121 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.2264. Min Act: -0.0003

Data Index: 605694 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.2087. Min Act: -0.0002

Data Index: 1192605 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.2076. Min Act: -0.0003

Data Index: 369876 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.2040. Min Act: -0.0003

Data Index: 480194 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.2018. Min Act: -0.0002

Data Index: 716051 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.2004. Min Act: -0.0002

Data Index: 460874 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1955. Min Act: -0.0003

Data Index: 459643 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1936. Min Act: -0.0002

Data Index: 645248 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1928. Min Act: -0.0003

Data Index: 596126 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1922. Min Act: -0.0002

Data Index: 481052 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1907. Min Act: -0.0003

Data Index: 635343 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1845. Min Act: -0.0003

Data Index: 935452 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1900. Min Act: -0.0003

Data Index: 908725 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1954. Min Act: -0.0003

Data Index: 310700 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1819. Min Act: -0.0003

Data Index: 1177609 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1871. Min Act: -0.0003

Data Index: 84127 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1806. Min Act: -0.0002

Data Index: 860399 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1926. Min Act: -0.0002

Data Index: 1140007 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1843. Min Act: -0.0002

Data Index: 759469 (C4 (Web Text))

Max Activating Token Index: 84