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

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

Neuron 4081 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.7609. Min Act: -0.0001

Data Index: 1403724 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.7507. Min Act: -0.0001

Data Index: 1436071 (Python Code)

Max Activating Token Index: 781

Text #2

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.7488. Min Act: -0.0001

Data Index: 1656481 (Python Code)

Max Activating Token Index: 908

Text #3

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.8079. Min Act: -0.0001

Data Index: 1420481 (Python Code)

Max Activating Token Index: 146

Text #4

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6844. Min Act: -0.0001

Data Index: 1507572 (Python Code)

Max Activating Token Index: 178

Text #5

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6250. Min Act: -0.0001

Data Index: 1367156 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6127. Min Act: -0.0001

Data Index: 1651881 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5623. Min Act: -0.0001

Data Index: 1271290 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5812. Min Act: -0.0001

Data Index: 1461523 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6362. Min Act: -0.0001

Data Index: 1650477 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5322. Min Act: -0.0001

Data Index: 1454425 (Python Code)

Max Activating Token Index: 484

Text #11

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5896. Min Act: -0.0001

Data Index: 1360700 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5363. Min Act: -0.0001

Data Index: 1575590 (Python Code)

Max Activating Token Index: 392

Text #13

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5320. Min Act: -0.0001

Data Index: 1392218 (Python Code)

Max Activating Token Index: 308

Text #14

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5434. Min Act: -0.0001

Data Index: 1576776 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5842. Min Act: -0.0001

Data Index: 267215 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5411. Min Act: -0.0001

Data Index: 1652911 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5665. Min Act: -0.0001

Data Index: 1508322 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.4852. Min Act: -0.0001

Data Index: 1449467 (Python Code)

Max Activating Token Index: 765

Text #19

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.4954. Min Act: -0.0001

Data Index: 1548395 (Python Code)

Max Activating Token Index: 413