Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2604 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1040790 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.5511. Min Act: -0.0000

Data Index: 1104510 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3872. Min Act: -0.0000

Data Index: 249618 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.1612. Min Act: -0.0000

Data Index: 329954 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.0490. Min Act: -0.0000

Data Index: 667844 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.3264. Min Act: -0.0000

Data Index: 518501 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.1205. Min Act: -0.0000

Data Index: 519892 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.1298. Min Act: -0.0000

Data Index: 226331 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.1563. Min Act: -0.0000

Data Index: 448801 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.1580. Min Act: -0.0000

Data Index: 853712 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1228799 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.0291. Min Act: -0.0000

Data Index: 739248 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.1906. Min Act: -0.0000

Data Index: 703858 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.5511. Min Range: -1.5511

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1308506 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 1.5511. Min Range: -1.5511

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1122729 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.5511. Min Range: -1.5511

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1045556 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1352872 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1135539 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 1.5511. Min Range: -1.5511

Max Act: 1.0464. Min Act: -0.0000

Data Index: 383190 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 1.5511. Min Range: -1.5511

Max Act: 0.9623. Min Act: -0.0000

Data Index: 665785 (C4 (Web Text))

Max Activating Token Index: 725