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

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

Neuron 778 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: 0.1903. Min Range: -0.1903

Max Act: 0.1832. Min Act: -0.0001

Data Index: 847343 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1903. Min Act: -0.0001

Data Index: 1011587 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1662. Min Act: -0.0000

Data Index: 802621 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1436. Min Act: -0.0000

Data Index: 731752 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1506. Min Act: -0.0000

Data Index: 370286 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1243302 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1191942 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1267277 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1321. Min Act: -0.0001

Data Index: 791685 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1239. Min Act: -0.0000

Data Index: 993356 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1302877 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1237. Min Act: -0.0000

Data Index: 506172 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1202. Min Act: -0.0001

Data Index: 809510 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1149213 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1317705 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1157. Min Act: -0.0000

Data Index: 952642 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1116. Min Act: -0.0000

Data Index: 31616 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1154. Min Act: -0.0000

Data Index: 275233 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1150. Min Act: -0.0001

Data Index: 682911 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1223677 (C4 (Web Text))

Max Activating Token Index: 889