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

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

Neuron 4862 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.8932. Min Act: 0.0000

Data Index: 1109105 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1305974 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.8305. Min Act: 0.0000

Data Index: 996991 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.7749. Min Act: -0.0000

Data Index: 119740 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.6939. Min Act: -0.0000

Data Index: 504314 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.6812. Min Act: 0.0000

Data Index: 426955 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.6894. Min Act: -0.0000

Data Index: 459367 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.6607. Min Act: -0.0000

Data Index: 890878 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.6395. Min Act: -0.0000

Data Index: 865889 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.6082. Min Act: -0.0000

Data Index: 751393 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.5701. Min Act: -0.0000

Data Index: 319394 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1215916 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.6143. Min Act: -0.0000

Data Index: 661987 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.5680. Min Act: 0.0000

Data Index: 8674 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.5708. Min Act: -0.0000

Data Index: 264792 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.5386. Min Act: -0.0000

Data Index: 726377 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.5148. Min Act: -0.0000

Data Index: 798181 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.5284. Min Act: -0.0000

Data Index: 202624 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.5230. Min Act: -0.0000

Data Index: 27313 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.8967. Min Range: -0.8967

Max Act: 0.5505. Min Act: -0.0000

Data Index: 442242 (C4 (Web Text))

Max Activating Token Index: 265