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

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

Neuron 4467 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: 0.9766. Min Range: -0.9766

Max Act: 0.9766. Min Act: -0.0000

Data Index: 129983 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8656. Min Act: -0.0000

Data Index: 764214 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8347. Min Act: -0.0000

Data Index: 992405 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8689. Min Act: -0.0000

Data Index: 791108 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8971. Min Act: -0.0000

Data Index: 696577 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1030173 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8873. Min Act: -0.0000

Data Index: 774977 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8538. Min Act: -0.0000

Data Index: 208489 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8538. Min Act: 0.0000

Data Index: 304945 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1218841 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1306887 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8385. Min Act: -0.0000

Data Index: 378968 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8394. Min Act: -0.0000

Data Index: 435639 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1196897 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8003. Min Act: -0.0000

Data Index: 360060 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7930. Min Act: -0.0000

Data Index: 729579 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7911. Min Act: -0.0000

Data Index: 463702 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8233. Min Act: -0.0000

Data Index: 414008 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8226. Min Act: -0.0000

Data Index: 995552 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7698. Min Act: -0.0000

Data Index: 538645 (C4 (Web Text))

Max Activating Token Index: 657