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

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

Neuron 1911 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.5119. Min Act: -0.0001

Data Index: 1099672 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.2383. Min Act: -0.0001

Data Index: 993267 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.0205. Min Act: -0.0001

Data Index: 789855 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.6097. Min Act: -0.0001

Data Index: 168061 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.9337. Min Act: -0.0001

Data Index: 1191659 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.5313. Min Act: -0.0001

Data Index: 653647 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.6991. Min Act: -0.0001

Data Index: 239717 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.5025. Min Act: -0.0001

Data Index: 468133 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.5143. Min Act: -0.0001

Data Index: 325585 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.7263. Min Act: -0.0001

Data Index: 1300762 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.3864. Min Act: -0.0001

Data Index: 697718 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.3832. Min Act: -0.0001

Data Index: 837170 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.1459. Min Act: -0.0001

Data Index: 1180246 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.2393. Min Act: -0.0001

Data Index: 614567 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.4859. Min Act: -0.0001

Data Index: 83767 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.4549. Min Act: -0.0001

Data Index: 830484 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.3160. Min Act: -0.0001

Data Index: 257915 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.2361. Min Act: -0.0001

Data Index: 947772 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.0746. Min Act: -0.0001

Data Index: 555201 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 3.5119. Min Range: -3.5119

Max Act: 2.1898. Min Act: -0.0001

Data Index: 1305814 (C4 (Web Text))

Max Activating Token Index: 44