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

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

Neuron 276 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.9817. Min Act: -0.0003

Data Index: 248487 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8092. Min Act: -0.0003

Data Index: 1308668 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.9282. Min Act: -0.0003

Data Index: 439076 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8719. Min Act: -0.0003

Data Index: 147521 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.9216. Min Act: -0.0003

Data Index: 414181 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8536. Min Act: -0.0003

Data Index: 1166443 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8746. Min Act: -0.0003

Data Index: 278617 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.7991. Min Act: -0.0003

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8442. Min Act: -0.0003

Data Index: 1134005 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8981. Min Act: -0.0003

Data Index: 826311 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8126. Min Act: -0.0003

Data Index: 764310 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.7584. Min Act: -0.0003

Data Index: 117797 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.7749. Min Act: -0.0003

Data Index: 639442 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8189. Min Act: -0.0003

Data Index: 208544 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8716. Min Act: -0.0003

Data Index: 740248 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8173. Min Act: -0.0003

Data Index: 722514 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8248. Min Act: -0.0003

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.9338. Min Act: -0.0003

Data Index: 734631 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8289. Min Act: -0.0003

Data Index: 764702 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8484. Min Act: -0.0003

Data Index: 1309785 (C4 (Web Text))

Max Activating Token Index: 363