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

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

Neuron 1862 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: 2.6877. Min Range: -2.6877

Max Act: 2.5720. Min Act: -0.0000

Data Index: 947944 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.6877. Min Act: -0.0000

Data Index: 899520 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.4131. Min Act: -0.0000

Data Index: 1212883 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.5357. Min Act: -0.0000

Data Index: 1302518 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.2270. Min Act: -0.0000

Data Index: 1332097 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.3382. Min Act: -0.0000

Data Index: 350629 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.4604. Min Act: -0.0000

Data Index: 334496 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.2031. Min Act: -0.0000

Data Index: 636445 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.2996. Min Act: -0.0000

Data Index: 1576229 (Python Code)

Max Activating Token Index: 171

Text #9

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.2729. Min Act: -0.0000

Data Index: 1398174 (Python Code)

Max Activating Token Index: 903

Text #10

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.4051. Min Act: -0.0000

Data Index: 1047902 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.2647. Min Act: -0.0000

Data Index: 1298668 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.3678. Min Act: -0.0000

Data Index: 255393 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.1132. Min Act: -0.0000

Data Index: 1564376 (Python Code)

Max Activating Token Index: 708

Text #14

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.1193. Min Act: -0.0000

Data Index: 853904 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.2175. Min Act: -0.0000

Data Index: 1242004 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.3318. Min Act: -0.0000

Data Index: 1310448 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.3239. Min Act: -0.0000

Data Index: 456452 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.1923. Min Act: -0.0000

Data Index: 1248397 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.1938. Min Act: -0.0000

Data Index: 478208 (C4 (Web Text))

Max Activating Token Index: 454