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

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

Neuron 3807 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1777. Min Act: -0.0000

Data Index: 53698 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1552. Min Act: -0.0000

Data Index: 769348 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1638. Min Act: -0.0000

Data Index: 478660 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1046785 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1389. Min Act: -0.0000

Data Index: 978969 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1102613 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1374. Min Act: -0.0000

Data Index: 980487 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1271906 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1282. Min Act: -0.0000

Data Index: 526944 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1071969 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1291. Min Act: -0.0000

Data Index: 520186 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1233. Min Act: -0.0000

Data Index: 510740 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1220. Min Act: -0.0001

Data Index: 675967 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1180. Min Act: -0.0000

Data Index: 519551 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1116. Min Act: -0.0000

Data Index: 633394 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1233. Min Act: -0.0000

Data Index: 197497 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1075620 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1141463 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1167595 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1219. Min Act: -0.0000

Data Index: 485757 (C4 (Web Text))

Max Activating Token Index: 831