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

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

Neuron 2570 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: 0.1713. Min Range: -0.1713

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1290516 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1427. Min Act: -0.0000

Data Index: 259914 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1430. Min Act: -0.0000

Data Index: 226952 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1382. Min Act: -0.0000

Data Index: 416507 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1224640 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1266. Min Act: -0.0000

Data Index: 199412 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1307. Min Act: -0.0000

Data Index: 507477 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1121903 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1268843 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1394219 (Python Code)

Max Activating Token Index: 733

Text #10

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1154. Min Act: 0.0000

Data Index: 322047 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1103. Min Act: -0.0000

Data Index: 621514 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1089. Min Act: -0.0000

Data Index: 848870 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1401310 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1084. Min Act: -0.0000

Data Index: 777792 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1117. Min Act: -0.0001

Data Index: 469211 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1016. Min Act: -0.0000

Data Index: 433889 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1035. Min Act: -0.0001

Data Index: 919950 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1074. Min Act: -0.0001

Data Index: 337932 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1057. Min Act: -0.0000

Data Index: 705078 (C4 (Web Text))

Max Activating Token Index: 981