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

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

Neuron 3522 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2469. Min Act: -0.0002

Data Index: 1266722 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2314. Min Act: -0.0002

Data Index: 283667 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2150. Min Act: -0.0001

Data Index: 373944 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2132. Min Act: -0.0001

Data Index: 864983 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2230. Min Act: -0.0002

Data Index: 627399 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2207. Min Act: -0.0002

Data Index: 79467 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2199. Min Act: -0.0002

Data Index: 931756 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2176. Min Act: -0.0002

Data Index: 822318 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2041. Min Act: -0.0002

Data Index: 875284 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1030549 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2044. Min Act: -0.0002

Data Index: 342673 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1917. Min Act: -0.0002

Data Index: 857010 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1953. Min Act: -0.0001

Data Index: 372383 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1974. Min Act: -0.0002

Data Index: 1167832 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1966. Min Act: -0.0002

Data Index: 444881 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1886. Min Act: -0.0002

Data Index: 707917 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1851. Min Act: -0.0001

Data Index: 855313 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1835. Min Act: -0.0002

Data Index: 108916 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1825. Min Act: -0.0002

Data Index: 994260 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1815. Min Act: -0.0002

Data Index: 185963 (C4 (Web Text))

Max Activating Token Index: 423