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

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

Neuron 1479 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.4203. Min Act: -0.0001

Data Index: 334158 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.4425. Min Act: -0.0001

Data Index: 411925 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.4641. Min Act: -0.0001

Data Index: 1596607 (Python Code)

Max Activating Token Index: 725

Text #3

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.3812. Min Act: -0.0001

Data Index: 531214 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.2672. Min Act: -0.0001

Data Index: 575266 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.1373. Min Act: -0.0001

Data Index: 1105659 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.2026. Min Act: -0.0001

Data Index: 1362146 (Python Code)

Max Activating Token Index: 829

Text #7

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.1382. Min Act: -0.0001

Data Index: 1449889 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.1793. Min Act: -0.0001

Data Index: 1645371 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.1582. Min Act: -0.0001

Data Index: 1508155 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.1270. Min Act: -0.0001

Data Index: 671086 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.1555. Min Act: -0.0001

Data Index: 3825 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.0741. Min Act: -0.0001

Data Index: 1602410 (Python Code)

Max Activating Token Index: 372

Text #13

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.0828. Min Act: -0.0001

Data Index: 792462 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.1367. Min Act: -0.0001

Data Index: 909836 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.1578. Min Act: -0.0001

Data Index: 709999 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.1252. Min Act: -0.0001

Data Index: 1229627 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.1072. Min Act: -0.0001

Data Index: 594703 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.2348. Min Act: -0.0001

Data Index: 1396433 (Python Code)

Max Activating Token Index: 778

Text #19

Max Range: 1.4641. Min Range: -1.4641

Max Act: 1.0957. Min Act: -0.0001

Data Index: 352485 (C4 (Web Text))

Max Activating Token Index: 39