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

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

Neuron 2171 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.2310. Min Act: -0.0001

Data Index: 984664 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.1528. Min Act: -0.0001

Data Index: 507860 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.1847. Min Act: -0.0001

Data Index: 1305376 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.1188. Min Act: -0.0001

Data Index: 501968 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.1683. Min Act: -0.0001

Data Index: 1351376 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.1355. Min Act: -0.0001

Data Index: 193075 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.0481. Min Act: -0.0001

Data Index: 1036834 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.0458. Min Act: -0.0001

Data Index: 575404 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.0383. Min Act: -0.0001

Data Index: 397905 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.0713. Min Act: -0.0001

Data Index: 219187 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.2310. Min Range: -1.2310

Max Act: 1.0890. Min Act: -0.0001

Data Index: 1059147 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.2310. Min Range: -1.2310

Max Act: 0.9668. Min Act: -0.0001

Data Index: 766441 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 1.2310. Min Range: -1.2310

Max Act: 0.9481. Min Act: -0.0001

Data Index: 1465173 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 1.2310. Min Range: -1.2310

Max Act: 0.9610. Min Act: -0.0001

Data Index: 821857 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 1.2310. Min Range: -1.2310

Max Act: 0.9016. Min Act: -0.0001

Data Index: 1144828 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 1.2310. Min Range: -1.2310

Max Act: 0.9429. Min Act: -0.0001

Data Index: 1185197 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 1.2310. Min Range: -1.2310

Max Act: 0.9340. Min Act: -0.0001

Data Index: 1489959 (Python Code)

Max Activating Token Index: 327

Text #17

Max Range: 1.2310. Min Range: -1.2310

Max Act: 0.9352. Min Act: -0.0001

Data Index: 465117 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 1.2310. Min Range: -1.2310

Max Act: 0.9341. Min Act: -0.0001

Data Index: 122394 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.2310. Min Range: -1.2310

Max Act: 0.9049. Min Act: -0.0001

Data Index: 847176 (C4 (Web Text))

Max Activating Token Index: 705