Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5826 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0646. Min Range: -4.0646

Max Act: 4.0646. Min Act: -0.0000

Data Index: 1113917 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 4.0646. Min Range: -4.0646

Max Act: 4.0124. Min Act: -0.0000

Data Index: 22937 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 4.0646. Min Range: -4.0646

Max Act: 3.8925. Min Act: -0.0000

Data Index: 962857 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 4.0646. Min Range: -4.0646

Max Act: 3.4912. Min Act: -0.0000

Data Index: 810513 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 4.0646. Min Range: -4.0646

Max Act: 3.4161. Min Act: -0.0001

Data Index: 625919 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 4.0646. Min Range: -4.0646

Max Act: 3.2236. Min Act: -0.0000

Data Index: 920126 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 4.0646. Min Range: -4.0646

Max Act: 3.0226. Min Act: -0.0000

Data Index: 1357189 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 4.0646. Min Range: -4.0646

Max Act: 3.0532. Min Act: -0.0000

Data Index: 61888 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 4.0646. Min Range: -4.0646

Max Act: 3.0347. Min Act: -0.0000

Data Index: 767735 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 4.0646. Min Range: -4.0646

Max Act: 3.0918. Min Act: -0.0000

Data Index: 814426 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 4.0646. Min Range: -4.0646

Max Act: 2.9092. Min Act: -0.0000

Data Index: 780539 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 4.0646. Min Range: -4.0646

Max Act: 2.7845. Min Act: -0.0000

Data Index: 83120 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 4.0646. Min Range: -4.0646

Max Act: 2.7657. Min Act: -0.0000

Data Index: 1173356 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 4.0646. Min Range: -4.0646

Max Act: 2.7993. Min Act: -0.0001

Data Index: 445888 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 4.0646. Min Range: -4.0646

Max Act: 2.8716. Min Act: -0.0000

Data Index: 595138 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 4.0646. Min Range: -4.0646

Max Act: 2.7176. Min Act: -0.0000

Data Index: 567030 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 4.0646. Min Range: -4.0646

Max Act: 2.8628. Min Act: -0.0000

Data Index: 1045560 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 4.0646. Min Range: -4.0646

Max Act: 2.8488. Min Act: -0.0000

Data Index: 755807 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 4.0646. Min Range: -4.0646

Max Act: 2.8387. Min Act: -0.0001

Data Index: 378324 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 4.0646. Min Range: -4.0646

Max Act: 2.8477. Min Act: -0.0000

Data Index: 1163893 (C4 (Web Text))

Max Activating Token Index: 694