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

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

Neuron 506 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: 0.1594. Min Range: -0.1594

Max Act: 0.1594. Min Act: -0.0002

Data Index: 853783 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1475. Min Act: -0.0002

Data Index: 99940 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1317. Min Act: -0.0002

Data Index: 214681 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1403. Min Act: -0.0002

Data Index: 1185909 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1224. Min Act: -0.0002

Data Index: 863476 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1300. Min Act: -0.0002

Data Index: 779074 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1235. Min Act: -0.0002

Data Index: 474585 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1352. Min Act: -0.0002

Data Index: 943703 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1335. Min Act: -0.0002

Data Index: 597187 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1332. Min Act: -0.0002

Data Index: 1149901 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1186. Min Act: -0.0002

Data Index: 684345 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1269. Min Act: -0.0002

Data Index: 849660 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1254. Min Act: -0.0002

Data Index: 946777 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1201. Min Act: -0.0002

Data Index: 221063 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1171. Min Act: -0.0002

Data Index: 1091633 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1192. Min Act: -0.0002

Data Index: 578332 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1141. Min Act: -0.0002

Data Index: 20453 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1067. Min Act: -0.0002

Data Index: 601173 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1139. Min Act: -0.0002

Data Index: 372539 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1148. Min Act: -0.0002

Data Index: 1074237 (C4 (Web Text))

Max Activating Token Index: 875