Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 32 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1567. Min Act: -0.0001

Data Index: 68075 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1438. Min Act: -0.0001

Data Index: 498649 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1378. Min Act: -0.0000

Data Index: 693782 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1372. Min Act: -0.0001

Data Index: 234336 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1341734 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1133185 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1271. Min Act: -0.0000

Data Index: 142425 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1304. Min Act: -0.0001

Data Index: 395322 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1305. Min Act: -0.0001

Data Index: 753802 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1252. Min Act: -0.0001

Data Index: 873418 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1303. Min Act: -0.0000

Data Index: 233114 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1333. Min Act: -0.0001

Data Index: 894692 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1261. Min Act: -0.0001

Data Index: 196011 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1253. Min Act: -0.0001

Data Index: 275784 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1201. Min Act: -0.0000

Data Index: 53447 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1215. Min Act: -0.0000

Data Index: 685702 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1208. Min Act: -0.0000

Data Index: 805039 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1050624 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1138. Min Act: -0.0000

Data Index: 216142 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1189765 (C4 (Web Text))

Max Activating Token Index: 1015