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

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

Neuron 3087 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1623. Min Range: -2.1623

Max Act: 2.1623. Min Act: -0.0000

Data Index: 542854 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.7629. Min Act: -0.0000

Data Index: 579248 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.4401. Min Act: -0.0000

Data Index: 24151 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.3220. Min Act: -0.0000

Data Index: 114311 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1634. Min Act: -0.0000

Data Index: 938138 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.3094. Min Act: -0.0000

Data Index: 1121852 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1940. Min Act: -0.0000

Data Index: 111971 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.2386. Min Act: -0.0000

Data Index: 490928 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1983. Min Act: -0.0000

Data Index: 449706 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.2010. Min Act: -0.0000

Data Index: 757311 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1560. Min Act: -0.0000

Data Index: 716099 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.2524. Min Act: -0.0000

Data Index: 309039 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1395. Min Act: -0.0000

Data Index: 1055696 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1852. Min Act: -0.0000

Data Index: 1347891 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1643. Min Act: -0.0000

Data Index: 1588734 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1116450 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1541. Min Act: -0.0000

Data Index: 102728 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1310. Min Act: -0.0000

Data Index: 222566 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1293821 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1114273 (C4 (Web Text))

Max Activating Token Index: 116