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

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

Neuron 3878 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: 1.7459. Min Range: -1.7459

Max Act: 1.7459. Min Act: -0.0000

Data Index: 173222 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.7215. Min Act: -0.0000

Data Index: 72936 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.7196. Min Act: -0.0000

Data Index: 1290530 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.6487. Min Act: -0.0000

Data Index: 272958 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5531. Min Act: -0.0000

Data Index: 1104370 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1230050 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5249. Min Act: -0.0000

Data Index: 863699 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4495. Min Act: -0.0000

Data Index: 97567 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4079. Min Act: -0.0000

Data Index: 714227 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4965. Min Act: -0.0000

Data Index: 74212 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4588. Min Act: -0.0000

Data Index: 719096 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5290. Min Act: -0.0000

Data Index: 1056326 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1521478 (Python Code)

Max Activating Token Index: 619

Text #13

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4031. Min Act: -0.0000

Data Index: 1185591 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4092. Min Act: -0.0000

Data Index: 683127 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4098. Min Act: -0.0000

Data Index: 238769 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4032. Min Act: -0.0000

Data Index: 559689 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4367. Min Act: -0.0000

Data Index: 80131 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4434. Min Act: -0.0000

Data Index: 952414 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.2652. Min Act: -0.0000

Data Index: 968935 (C4 (Web Text))

Max Activating Token Index: 887