Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2164 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.6147. Min Act: -0.0000

Data Index: 1017294 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.4432. Min Act: -0.0000

Data Index: 271474 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.5227. Min Act: -0.0000

Data Index: 1083110 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.5001. Min Act: -0.0000

Data Index: 529666 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.5158. Min Act: -0.0000

Data Index: 524876 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1354336 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.3578. Min Act: -0.0000

Data Index: 125213 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.3359. Min Act: -0.0000

Data Index: 378302 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.2170. Min Act: -0.0000

Data Index: 123910 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.1890. Min Act: -0.0000

Data Index: 976036 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.2628. Min Act: -0.0000

Data Index: 593504 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.2545. Min Act: -0.0000

Data Index: 518190 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.2545. Min Act: -0.0000

Data Index: 245940 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.1825. Min Act: -0.0000

Data Index: 80347 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.1806. Min Act: -0.0000

Data Index: 543527 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1238075 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.1707. Min Act: -0.0000

Data Index: 829536 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.1584. Min Act: -0.0000

Data Index: 853507 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.1268. Min Act: -0.0000

Data Index: 144303 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.6147. Min Range: -1.6147

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1004677 (C4 (Web Text))

Max Activating Token Index: 287