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

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

Neuron 1434 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: 0.2329. Min Range: -0.2329

Max Act: 0.2329. Min Act: -0.0000

Data Index: 955884 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.2167. Min Act: 0.0000

Data Index: 1134450 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1496. Min Act: -0.0000

Data Index: 585014 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1439. Min Act: -0.0000

Data Index: 537073 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1020277 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1448. Min Act: -0.0000

Data Index: 313114 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1052742 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1624927 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1316. Min Act: -0.0000

Data Index: 814264 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1168. Min Act: -0.0000

Data Index: 956880 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1044470 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1064. Min Act: -0.0000

Data Index: 888044 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1273. Min Act: -0.0000

Data Index: 183752 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1234955 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1137. Min Act: -0.0000

Data Index: 162425 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1578627 (Python Code)

Max Activating Token Index: 209

Text #16

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1051038 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1060. Min Act: -0.0000

Data Index: 822578 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1186. Min Act: -0.0000

Data Index: 901502 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1049. Min Act: 0.0001

Data Index: 4407 (C4 (Web Text))

Max Activating Token Index: 725