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

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

Neuron 1265 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6445. Min Act: -0.0000

Data Index: 232456 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6884. Min Act: -0.0000

Data Index: 735657 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6763. Min Act: -0.0000

Data Index: 881704 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1265218 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1243912 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6046. Min Act: -0.0000

Data Index: 538804 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6441. Min Act: 0.0000

Data Index: 412367 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6379. Min Act: -0.0000

Data Index: 874071 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6280. Min Act: 0.0000

Data Index: 987204 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6451. Min Act: -0.0000

Data Index: 550497 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1119795 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6363. Min Act: -0.0000

Data Index: 62577 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6390. Min Act: -0.0000

Data Index: 303112 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6206. Min Act: -0.0000

Data Index: 769136 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5882. Min Act: 0.0001

Data Index: 1078689 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5891. Min Act: -0.0000

Data Index: 270198 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5860. Min Act: -0.0000

Data Index: 463646 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5586. Min Act: 0.0000

Data Index: 55872 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1007430 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5896. Min Act: -0.0000

Data Index: 878697 (C4 (Web Text))

Max Activating Token Index: 806