Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2960 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2409. Min Range: -1.2409

Max Act: 1.2409. Min Act: -0.0001

Data Index: 1122995 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9516. Min Act: -0.0001

Data Index: 1110634 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9580. Min Act: -0.0001

Data Index: 1174602 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9297. Min Act: -0.0001

Data Index: 604711 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9446. Min Act: -0.0001

Data Index: 910392 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8556. Min Act: -0.0001

Data Index: 1357062 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9233. Min Act: -0.0001

Data Index: 665348 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8797. Min Act: -0.0001

Data Index: 1101737 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8694. Min Act: -0.0001

Data Index: 1280386 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8683. Min Act: -0.0001

Data Index: 763444 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8317. Min Act: -0.0001

Data Index: 563997 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.7930. Min Act: -0.0001

Data Index: 43239 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8496. Min Act: -0.0001

Data Index: 688496 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8350. Min Act: -0.0001

Data Index: 1080660 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8036. Min Act: -0.0001

Data Index: 581711 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8047. Min Act: -0.0001

Data Index: 483075 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8280. Min Act: -0.0001

Data Index: 832079 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8480. Min Act: -0.0001

Data Index: 996725 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1181657 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8107. Min Act: -0.0001

Data Index: 170583 (C4 (Web Text))

Max Activating Token Index: 112