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

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

Neuron 377 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1490. Min Act: -0.0002

Data Index: 597515 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1444. Min Act: -0.0002

Data Index: 175492 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1484. Min Act: -0.0002

Data Index: 259300 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1292460 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1331. Min Act: -0.0002

Data Index: 1277742 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1205. Min Act: -0.0002

Data Index: 660501 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1279. Min Act: -0.0002

Data Index: 219802 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1203. Min Act: -0.0002

Data Index: 1272589 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1224. Min Act: -0.0002

Data Index: 787995 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1223. Min Act: -0.0002

Data Index: 160234 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1262690 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1140. Min Act: -0.0002

Data Index: 672764 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1126. Min Act: -0.0002

Data Index: 714753 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1182. Min Act: -0.0002

Data Index: 589174 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1208. Min Act: -0.0002

Data Index: 60556 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1125. Min Act: -0.0002

Data Index: 668522 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1164. Min Act: -0.0002

Data Index: 966434 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1236. Min Act: -0.0002

Data Index: 224258 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1173. Min Act: -0.0002

Data Index: 590849 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1153. Min Act: -0.0002

Data Index: 155445 (C4 (Web Text))

Max Activating Token Index: 350