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

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

Neuron 4832 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: 1.6710. Min Range: -1.6710

Max Act: 1.6023. Min Act: -0.0000

Data Index: 10519 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.6710. Min Act: -0.0000

Data Index: 1297528 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.5687. Min Act: -0.0001

Data Index: 1115730 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4942. Min Act: -0.0001

Data Index: 450501 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3965. Min Act: -0.0000

Data Index: 891859 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2030. Min Act: -0.0000

Data Index: 422093 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2136. Min Act: -0.0001

Data Index: 870783 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2090. Min Act: -0.0000

Data Index: 943032 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3330. Min Act: -0.0000

Data Index: 1227512 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1110. Min Act: -0.0000

Data Index: 995626 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1407. Min Act: -0.0001

Data Index: 660576 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1231. Min Act: -0.0001

Data Index: 937911 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.0178. Min Act: -0.0000

Data Index: 506135 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1472. Min Act: -0.0000

Data Index: 98514 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1172991 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1447. Min Act: -0.0000

Data Index: 627051 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1405. Min Act: -0.0001

Data Index: 725453 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1658. Min Act: -0.0000

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1478. Min Act: -0.0000

Data Index: 266570 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.1224. Min Act: -0.0001

Data Index: 39708 (C4 (Web Text))

Max Activating Token Index: 251