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

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

Neuron 162 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5135. Min Range: -4.5135

Max Act: 4.5135. Min Act: -0.0000

Data Index: 648426 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 4.5135. Min Range: -4.5135

Max Act: 4.2023. Min Act: -0.0000

Data Index: 16294 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.7117. Min Act: -0.0000

Data Index: 1130464 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.7717. Min Act: -0.0000

Data Index: 747194 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.8958. Min Act: -0.0000

Data Index: 1298456 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.4792. Min Act: -0.0000

Data Index: 1351236 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.6954. Min Act: -0.0000

Data Index: 293472 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.4643. Min Act: -0.0000

Data Index: 1200236 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.6859. Min Act: -0.0000

Data Index: 644442 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.6625. Min Act: -0.0000

Data Index: 884702 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.4061. Min Act: -0.0000

Data Index: 226076 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.0029. Min Act: -0.0000

Data Index: 379779 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.2665. Min Act: -0.0000

Data Index: 20823 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.1147. Min Act: -0.0000

Data Index: 1303925 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.1106. Min Act: -0.0000

Data Index: 1174563 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 4.5135. Min Range: -4.5135

Max Act: 2.9617. Min Act: -0.0000

Data Index: 523017 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 4.5135. Min Range: -4.5135

Max Act: 2.9315. Min Act: -0.0000

Data Index: 1013478 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.1807. Min Act: -0.0000

Data Index: 803724 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 4.5135. Min Range: -4.5135

Max Act: 2.8927. Min Act: -0.0000

Data Index: 1165039 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 4.5135. Min Range: -4.5135

Max Act: 3.0242. Min Act: -0.0000

Data Index: 369382 (C4 (Web Text))

Max Activating Token Index: 833