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

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

Neuron 1307 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: 2.4613. Min Range: -2.4613

Max Act: 2.4613. Min Act: -0.0000

Data Index: 1637839 (Python Code)

Max Activating Token Index: 394

Text #1

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.1221. Min Act: -0.0000

Data Index: 1427108 (Python Code)

Max Activating Token Index: 342

Text #2

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.8355. Min Act: -0.0000

Data Index: 1650842 (Python Code)

Max Activating Token Index: 416

Text #3

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.8304. Min Act: -0.0000

Data Index: 1520055 (Python Code)

Max Activating Token Index: 121

Text #4

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.7824. Min Act: -0.0000

Data Index: 204426 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.9694. Min Act: -0.0000

Data Index: 1498479 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.8620. Min Act: -0.0000

Data Index: 1479203 (Python Code)

Max Activating Token Index: 631

Text #7

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.5697. Min Act: -0.0000

Data Index: 1048446 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.4498. Min Act: -0.0000

Data Index: 1136027 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.4985. Min Act: -0.0000

Data Index: 473000 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.3962. Min Act: -0.0000

Data Index: 454153 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.4426. Min Act: -0.0000

Data Index: 1539756 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.4595. Min Act: -0.0000

Data Index: 1388513 (Python Code)

Max Activating Token Index: 527

Text #13

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1396895 (Python Code)

Max Activating Token Index: 878

Text #14

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1555758 (Python Code)

Max Activating Token Index: 426

Text #15

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.3595. Min Act: -0.0000

Data Index: 1415872 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1589357 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.2919. Min Act: -0.0000

Data Index: 615476 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.3649. Min Act: -0.0000

Data Index: 1050524 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.3488. Min Act: -0.0000

Data Index: 979906 (C4 (Web Text))

Max Activating Token Index: 9