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

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

Neuron 3721 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.8142. Min Act: -0.0000

Data Index: 357088 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.8676. Min Act: -0.0000

Data Index: 265738 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.8164. Min Act: 0.0000

Data Index: 727954 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.7172. Min Act: -0.0000

Data Index: 985286 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.7272. Min Act: -0.0000

Data Index: 541500 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6722. Min Act: -0.0000

Data Index: 918989 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6481. Min Act: -0.0000

Data Index: 880029 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1107501 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1157966 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1358682 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6682. Min Act: -0.0000

Data Index: 126505 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6393. Min Act: -0.0000

Data Index: 222991 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1296185 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6154. Min Act: -0.0000

Data Index: 693800 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6323. Min Act: -0.0000

Data Index: 574160 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6214. Min Act: -0.0000

Data Index: 363614 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1046732 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6110. Min Act: -0.0000

Data Index: 677602 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6860. Min Act: -0.0000

Data Index: 962558 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.5300. Min Act: -0.0000

Data Index: 364043 (C4 (Web Text))

Max Activating Token Index: 748