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

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

Neuron 4738 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: 4.5775. Min Range: -4.5775

Max Act: 4.5775. Min Act: -0.0000

Data Index: 912258 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 4.5775. Min Range: -4.5775

Max Act: 3.4152. Min Act: -0.0000

Data Index: 678944 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 4.5775. Min Range: -4.5775

Max Act: 3.1155. Min Act: -0.0000

Data Index: 1230799 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.8225. Min Act: -0.0000

Data Index: 1354426 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.6952. Min Act: -0.0000

Data Index: 867888 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 4.5775. Min Range: -4.5775

Max Act: 3.0516. Min Act: -0.0000

Data Index: 267648 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.8376. Min Act: -0.0000

Data Index: 1170031 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.3697. Min Act: -0.0000

Data Index: 1181518 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.7114. Min Act: -0.0000

Data Index: 218945 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.6319. Min Act: -0.0000

Data Index: 434415 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.8708. Min Act: -0.0000

Data Index: 259453 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.7558. Min Act: -0.0000

Data Index: 586650 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.4594. Min Act: -0.0000

Data Index: 868201 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.7846. Min Act: -0.0000

Data Index: 1075039 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.5969. Min Act: -0.0000

Data Index: 338540 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.6086. Min Act: -0.0000

Data Index: 638957 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.5075. Min Act: -0.0000

Data Index: 833345 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.3623. Min Act: -0.0001

Data Index: 831446 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.2444. Min Act: -0.0000

Data Index: 936981 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 4.5775. Min Range: -4.5775

Max Act: 2.3597. Min Act: -0.0000

Data Index: 95742 (C4 (Web Text))

Max Activating Token Index: 236