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

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

Neuron 1592 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.9524. Min Act: -0.0000

Data Index: 517734 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.9434. Min Act: -0.0000

Data Index: 790185 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.8261. Min Act: -0.0001

Data Index: 1145097 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.7385. Min Act: -0.0000

Data Index: 230878 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.7319. Min Act: -0.0000

Data Index: 493802 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.7045. Min Act: -0.0000

Data Index: 411483 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6904. Min Act: -0.0001

Data Index: 776847 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6967. Min Act: -0.0001

Data Index: 126963 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6539. Min Act: -0.0001

Data Index: 843189 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6874. Min Act: -0.0000

Data Index: 874194 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6573. Min Act: -0.0001

Data Index: 1039159 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1194979 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6332. Min Act: -0.0001

Data Index: 1021922 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6139. Min Act: -0.0000

Data Index: 408703 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6071. Min Act: -0.0000

Data Index: 429412 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5909. Min Act: -0.0001

Data Index: 356186 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5979. Min Act: -0.0000

Data Index: 766070 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5824. Min Act: -0.0001

Data Index: 781872 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6037. Min Act: -0.0001

Data Index: 589888 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5582. Min Act: -0.0000

Data Index: 851987 (C4 (Web Text))

Max Activating Token Index: 510