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

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

Neuron 4531 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1713. Min Range: -3.1713

Max Act: 3.1713. Min Act: -0.0000

Data Index: 1340570 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.7541. Min Act: -0.0000

Data Index: 447229 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.4662. Min Act: -0.0000

Data Index: 110545 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.3128. Min Act: -0.0000

Data Index: 630520 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.2586. Min Act: -0.0000

Data Index: 1286506 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.3415. Min Act: -0.0000

Data Index: 777834 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.3268. Min Act: -0.0000

Data Index: 426152 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.2869. Min Act: -0.0000

Data Index: 599060 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.5478. Min Act: -0.0000

Data Index: 147916 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.1165. Min Act: -0.0000

Data Index: 606701 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.3558. Min Act: -0.0000

Data Index: 567766 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.2193. Min Act: -0.0000

Data Index: 580794 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.0833. Min Act: -0.0000

Data Index: 282645 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.1771. Min Act: -0.0000

Data Index: 743618 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.0543. Min Act: -0.0000

Data Index: 341782 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.0435. Min Act: -0.0000

Data Index: 425658 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.0486. Min Act: -0.0000

Data Index: 416391 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.1443. Min Act: -0.0000

Data Index: 927978 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.1358. Min Act: -0.0000

Data Index: 354406 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 3.1713. Min Range: -3.1713

Max Act: 2.0257. Min Act: -0.0000

Data Index: 188526 (C4 (Web Text))

Max Activating Token Index: 29