Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2046 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1677. Min Act: -0.0001

Data Index: 338940 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1538. Min Act: -0.0001

Data Index: 141317 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1491. Min Act: -0.0001

Data Index: 764265 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1263. Min Act: -0.0001

Data Index: 77750 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1437. Min Act: -0.0001

Data Index: 902213 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1161077 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1291931 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1324. Min Act: -0.0001

Data Index: 1336071 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1055997 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1218. Min Act: -0.0001

Data Index: 418886 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1166. Min Act: -0.0001

Data Index: 666011 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1353264 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1187. Min Act: -0.0001

Data Index: 760419 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1189. Min Act: -0.0001

Data Index: 737487 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1100. Min Act: -0.0001

Data Index: 150740 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1228. Min Act: -0.0001

Data Index: 13186 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1147. Min Act: -0.0001

Data Index: 832276 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1227. Min Act: -0.0001

Data Index: 944797 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1110. Min Act: -0.0001

Data Index: 223606 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1031. Min Act: -0.0001

Data Index: 422245 (C4 (Web Text))

Max Activating Token Index: 535