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

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

Neuron 2606 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.5161. Min Act: -0.0000

Data Index: 487663 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.5026. Min Act: -0.0000

Data Index: 778101 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4619. Min Act: -0.0000

Data Index: 662255 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4570. Min Act: -0.0000

Data Index: 819575 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1056892 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4439. Min Act: -0.0000

Data Index: 785937 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1566336 (Python Code)

Max Activating Token Index: 567

Text #7

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4527. Min Act: -0.0000

Data Index: 230155 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1328492 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1161030 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4287. Min Act: -0.0000

Data Index: 885987 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4028. Min Act: -0.0000

Data Index: 800197 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4202. Min Act: -0.0000

Data Index: 65988 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4252. Min Act: -0.0000

Data Index: 590847 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4220. Min Act: -0.0000

Data Index: 224494 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4325. Min Act: -0.0000

Data Index: 904095 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4424. Min Act: -0.0000

Data Index: 927168 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4206. Min Act: -0.0000

Data Index: 794519 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1234957 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4155. Min Act: -0.0000

Data Index: 838407 (C4 (Web Text))

Max Activating Token Index: 825