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

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

Neuron 3221 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4310. Min Range: -2.4310

Max Act: 2.4310. Min Act: -0.0000

Data Index: 1049596 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 2.4310. Min Range: -2.4310

Max Act: 2.1272. Min Act: -0.0000

Data Index: 1124655 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.7088. Min Act: -0.0000

Data Index: 252166 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.8787. Min Act: -0.0000

Data Index: 1597388 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.6931. Min Act: -0.0000

Data Index: 1653379 (Python Code)

Max Activating Token Index: 514

Text #5

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.3344. Min Act: -0.0000

Data Index: 1639081 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.4075. Min Act: -0.0000

Data Index: 617858 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.2753. Min Act: -0.0000

Data Index: 20430 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.3619. Min Act: -0.0000

Data Index: 1200425 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.3619. Min Act: -0.0000

Data Index: 804595 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.3167. Min Act: -0.0000

Data Index: 680487 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1305235 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.3110. Min Act: -0.0000

Data Index: 1629141 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.3812. Min Act: -0.0000

Data Index: 670844 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1138370 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.2697. Min Act: -0.0000

Data Index: 515243 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.2652. Min Act: -0.0000

Data Index: 380484 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.1769. Min Act: -0.0000

Data Index: 1596409 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.2189. Min Act: -0.0000

Data Index: 945838 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 2.4310. Min Range: -2.4310

Max Act: 1.2187. Min Act: -0.0000

Data Index: 84942 (C4 (Web Text))

Max Activating Token Index: 529