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

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

Neuron 3305 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: 0.2402. Min Range: -0.2402

Max Act: 0.2346. Min Act: -0.0000

Data Index: 72022 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1276036 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2402. Min Act: -0.0000

Data Index: 437659 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2146. Min Act: -0.0000

Data Index: 543994 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1032624 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1989. Min Act: -0.0000

Data Index: 859095 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1995. Min Act: -0.0000

Data Index: 363452 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1834. Min Act: -0.0000

Data Index: 218614 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1211662 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1875. Min Act: -0.0000

Data Index: 44794 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1849. Min Act: -0.0000

Data Index: 940233 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1129614 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1676. Min Act: -0.0000

Data Index: 721740 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1818. Min Act: -0.0000

Data Index: 190549 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1729. Min Act: -0.0000

Data Index: 570077 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1746. Min Act: -0.0000

Data Index: 381088 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1568. Min Act: -0.0000

Data Index: 980193 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1900. Min Act: -0.0000

Data Index: 503087 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1401805 (Python Code)

Max Activating Token Index: 521

Text #19

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1831. Min Act: -0.0000

Data Index: 341936 (C4 (Web Text))

Max Activating Token Index: 900