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

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

Neuron 3206 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.2110. Min Range: -3.2110

Max Act: 3.2110. Min Act: -0.0001

Data Index: 335936 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 3.2110. Min Range: -3.2110

Max Act: 2.6418. Min Act: -0.0001

Data Index: 1326407 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 3.2110. Min Range: -3.2110

Max Act: 2.4948. Min Act: -0.0001

Data Index: 850170 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 3.2110. Min Range: -3.2110

Max Act: 2.4832. Min Act: -0.0001

Data Index: 1110723 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 3.2110. Min Range: -3.2110

Max Act: 2.3156. Min Act: -0.0001

Data Index: 1028637 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 3.2110. Min Range: -3.2110

Max Act: 2.2413. Min Act: -0.0001

Data Index: 1287420 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 3.2110. Min Range: -3.2110

Max Act: 2.2476. Min Act: -0.0001

Data Index: 393320 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 3.2110. Min Range: -3.2110

Max Act: 2.1813. Min Act: -0.0001

Data Index: 1318364 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 3.2110. Min Range: -3.2110

Max Act: 2.2688. Min Act: -0.0001

Data Index: 1163384 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 3.2110. Min Range: -3.2110

Max Act: 1.9868. Min Act: -0.0001

Data Index: 1157758 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 3.2110. Min Range: -3.2110

Max Act: 2.0964. Min Act: -0.0001

Data Index: 1065297 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 3.2110. Min Range: -3.2110

Max Act: 1.8626. Min Act: -0.0001

Data Index: 1196947 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 3.2110. Min Range: -3.2110

Max Act: 2.0529. Min Act: -0.0001

Data Index: 972426 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 3.2110. Min Range: -3.2110

Max Act: 1.9320. Min Act: -0.0001

Data Index: 1206346 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 3.2110. Min Range: -3.2110

Max Act: 1.8212. Min Act: -0.0001

Data Index: 1082361 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 3.2110. Min Range: -3.2110

Max Act: 1.9655. Min Act: -0.0001

Data Index: 97458 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 3.2110. Min Range: -3.2110

Max Act: 1.8668. Min Act: -0.0001

Data Index: 46440 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 3.2110. Min Range: -3.2110

Max Act: 1.8619. Min Act: -0.0001

Data Index: 1345967 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 3.2110. Min Range: -3.2110

Max Act: 1.8490. Min Act: -0.0001

Data Index: 889809 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 3.2110. Min Range: -3.2110

Max Act: 1.8448. Min Act: -0.0001

Data Index: 694557 (C4 (Web Text))

Max Activating Token Index: 375