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

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

Neuron 2066 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.6256. Min Act: -0.0000

Data Index: 1336521 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.1323. Min Act: -0.0000

Data Index: 1186813 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.0816. Min Act: -0.0000

Data Index: 906805 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.1857. Min Act: -0.0000

Data Index: 710233 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.1681. Min Act: -0.0000

Data Index: 172383 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.1707. Min Act: -0.0000

Data Index: 1145656 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.1457. Min Act: -0.0000

Data Index: 1081689 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.1050. Min Act: -0.0000

Data Index: 743344 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.0853. Min Act: -0.0000

Data Index: 548863 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.0440. Min Act: -0.0000

Data Index: 351511 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 2.6256. Min Range: -2.6256

Max Act: 1.9431. Min Act: -0.0000

Data Index: 1211855 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.0302. Min Act: -0.0000

Data Index: 1242633 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 2.6256. Min Range: -2.6256

Max Act: 1.8820. Min Act: -0.0001

Data Index: 1115102 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.0898. Min Act: -0.0000

Data Index: 560088 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 2.6256. Min Range: -2.6256

Max Act: 1.8432. Min Act: -0.0000

Data Index: 969875 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 2.6256. Min Range: -2.6256

Max Act: 1.9741. Min Act: -0.0000

Data Index: 674406 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 2.6256. Min Range: -2.6256

Max Act: 2.0547. Min Act: -0.0000

Data Index: 419591 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 2.6256. Min Range: -2.6256

Max Act: 1.9518. Min Act: -0.0000

Data Index: 1082794 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 2.6256. Min Range: -2.6256

Max Act: 1.9110. Min Act: -0.0000

Data Index: 719286 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 2.6256. Min Range: -2.6256

Max Act: 1.9055. Min Act: -0.0000

Data Index: 337071 (C4 (Web Text))

Max Activating Token Index: 58