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

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

Neuron 3245 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: 0.1418. Min Range: -0.1418

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1418934 (Python Code)

Max Activating Token Index: 532

Text #1

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1629824 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1024722 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1308. Min Act: -0.0001

Data Index: 1600434 (Python Code)

Max Activating Token Index: 355

Text #4

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1654330 (Python Code)

Max Activating Token Index: 277

Text #5

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1361290 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1591913 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1203. Min Act: -0.0001

Data Index: 1370837 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1602650 (Python Code)

Max Activating Token Index: 868

Text #9

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1437729 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1613520 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1184. Min Act: -0.0000

Data Index: 738204 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1182. Min Act: -0.0000

Data Index: 5686 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1393496 (Python Code)

Max Activating Token Index: 151

Text #14

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1080892 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1473492 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1570885 (Python Code)

Max Activating Token Index: 681

Text #17

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1409998 (Python Code)

Max Activating Token Index: 483

Text #18

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1362994 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1138. Min Act: -0.0001

Data Index: 14943 (C4 (Web Text))

Max Activating Token Index: 308