Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1931 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3524. Min Range: -2.3524

Max Act: 2.3385. Min Act: -0.0000

Data Index: 62750 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 2.3524. Min Range: -2.3524

Max Act: 2.3118. Min Act: -0.0000

Data Index: 400549 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 2.3524. Min Range: -2.3524

Max Act: 2.3524. Min Act: -0.0000

Data Index: 1156291 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 2.3524. Min Range: -2.3524

Max Act: 2.1379. Min Act: -0.0000

Data Index: 1129809 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 2.3524. Min Range: -2.3524

Max Act: 2.0000. Min Act: -0.0000

Data Index: 771507 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 2.3524. Min Range: -2.3524

Max Act: 2.0805. Min Act: -0.0000

Data Index: 1339590 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 2.3524. Min Range: -2.3524

Max Act: 2.0683. Min Act: -0.0000

Data Index: 503113 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 2.3524. Min Range: -2.3524

Max Act: 2.1393. Min Act: -0.0000

Data Index: 1155128 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 2.3524. Min Range: -2.3524

Max Act: 2.0291. Min Act: -0.0000

Data Index: 834055 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.8841. Min Act: -0.0000

Data Index: 302818 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.9962. Min Act: -0.0000

Data Index: 557653 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.9671. Min Act: -0.0000

Data Index: 189960 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.9599. Min Act: -0.0000

Data Index: 486823 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.9228. Min Act: -0.0000

Data Index: 1028227 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.9159. Min Act: -0.0000

Data Index: 998987 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.8253. Min Act: -0.0000

Data Index: 1234706 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.9890. Min Act: -0.0000

Data Index: 722438 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.8812. Min Act: -0.0000

Data Index: 835276 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.8635. Min Act: -0.0000

Data Index: 687195 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 2.3524. Min Range: -2.3524

Max Act: 1.8525. Min Act: -0.0000

Data Index: 321920 (C4 (Web Text))

Max Activating Token Index: 131