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

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

Neuron 2436 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1487. Min Act: -0.0001

Data Index: 129532 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1140401 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1414. Min Act: -0.0000

Data Index: 754626 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1402. Min Act: -0.0001

Data Index: 188261 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1057374 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1417. Min Act: -0.0000

Data Index: 918023 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1259. Min Act: -0.0001

Data Index: 775472 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1308. Min Act: -0.0001

Data Index: 258510 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1482787 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1203. Min Act: -0.0000

Data Index: 823349 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1216869 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1179. Min Act: -0.0001

Data Index: 632511 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1101395 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1618100 (Python Code)

Max Activating Token Index: 506

Text #14

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1656845 (Python Code)

Max Activating Token Index: 473

Text #15

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1114. Min Act: -0.0001

Data Index: 1379330 (Python Code)

Max Activating Token Index: 109

Text #16

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1100. Min Act: -0.0001

Data Index: 766008 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1176. Min Act: -0.0000

Data Index: 208773 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1134. Min Act: -0.0001

Data Index: 597591 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1137. Min Act: -0.0001

Data Index: 430846 (C4 (Web Text))

Max Activating Token Index: 706