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

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

Neuron 686 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1604. Min Act: -0.0001

Data Index: 329370 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1245. Min Act: -0.0001

Data Index: 376729 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1052205 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1052346 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1209. Min Act: -0.0001

Data Index: 933749 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1116937 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1163271 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1285536 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1140. Min Act: -0.0001

Data Index: 884176 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1142. Min Act: -0.0001

Data Index: 687253 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1211310 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1132. Min Act: -0.0001

Data Index: 767495 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1135. Min Act: -0.0001

Data Index: 379488 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1113. Min Act: -0.0001

Data Index: 28714 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1123. Min Act: -0.0001

Data Index: 812532 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1101. Min Act: -0.0001

Data Index: 1017131 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1168. Min Act: -0.0001

Data Index: 62721 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1155. Min Act: -0.0001

Data Index: 978375 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1183. Min Act: -0.0001

Data Index: 763327 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1065. Min Act: -0.0001

Data Index: 198733 (C4 (Web Text))

Max Activating Token Index: 546