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

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

Neuron 1774 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: 1.0781. Min Range: -1.0781

Max Act: 1.0116. Min Act: -0.0001

Data Index: 1056803 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 1.0781. Min Range: -1.0781

Max Act: 1.0781. Min Act: -0.0001

Data Index: 658921 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 1.0781. Min Range: -1.0781

Max Act: 1.0391. Min Act: -0.0001

Data Index: 1204376 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.0781. Min Range: -1.0781

Max Act: 1.0070. Min Act: -0.0001

Data Index: 73516 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 1.0781. Min Range: -1.0781

Max Act: 1.0035. Min Act: -0.0001

Data Index: 894424 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.9305. Min Act: -0.0001

Data Index: 1639727 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.9757. Min Act: -0.0001

Data Index: 156089 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.8304. Min Act: -0.0001

Data Index: 1121072 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.9494. Min Act: -0.0001

Data Index: 1175246 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.9289. Min Act: -0.0001

Data Index: 327155 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.8576. Min Act: -0.0001

Data Index: 793724 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.9402. Min Act: -0.0001

Data Index: 1569289 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.9373. Min Act: -0.0001

Data Index: 566769 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.8629. Min Act: -0.0001

Data Index: 577564 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.9469. Min Act: -0.0001

Data Index: 737621 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.9212. Min Act: -0.0001

Data Index: 520472 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.9138. Min Act: -0.0001

Data Index: 869438 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.8877. Min Act: -0.0001

Data Index: 792722 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.8272. Min Act: -0.0001

Data Index: 81107 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.0781. Min Range: -1.0781

Max Act: 0.9216. Min Act: -0.0001

Data Index: 484064 (C4 (Web Text))

Max Activating Token Index: 7