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

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

Neuron 1778 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1945. Min Act: -0.0002

Data Index: 462187 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1744. Min Act: -0.0002

Data Index: 16636 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1674. Min Act: -0.0002

Data Index: 811799 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1143758 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1299274 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1143. Min Act: -0.0002

Data Index: 964903 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1078. Min Act: -0.0002

Data Index: 189911 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1183. Min Act: -0.0002

Data Index: 711486 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1348380 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1061. Min Act: -0.0002

Data Index: 459086 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1200. Min Act: -0.0002

Data Index: 1099916 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1047. Min Act: -0.0003

Data Index: 1014367 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1046. Min Act: -0.0002

Data Index: 647021 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0996. Min Act: -0.0002

Data Index: 53191 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1139. Min Act: -0.0002

Data Index: 17591 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1105. Min Act: -0.0002

Data Index: 1294595 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1246. Min Act: -0.0002

Data Index: 917921 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0996. Min Act: -0.0002

Data Index: 456065 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1119. Min Act: -0.0002

Data Index: 253959 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1044. Min Act: -0.0003

Data Index: 35314 (C4 (Web Text))

Max Activating Token Index: 55