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

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

Neuron 2852 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.9635. Min Act: -0.0000

Data Index: 643600 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.7652. Min Act: -0.0000

Data Index: 575859 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.6680. Min Act: -0.0000

Data Index: 1334586 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.6606. Min Act: -0.0000

Data Index: 227592 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.7061. Min Act: -0.0000

Data Index: 898682 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.6081. Min Act: -0.0000

Data Index: 423740 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.6031. Min Act: -0.0000

Data Index: 447662 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.6855. Min Act: -0.0000

Data Index: 1025798 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.6772. Min Act: -0.0000

Data Index: 924834 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.7444. Min Act: -0.0000

Data Index: 954992 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.6329. Min Act: -0.0000

Data Index: 868057 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.6465. Min Act: -0.0000

Data Index: 143669 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.5487. Min Act: -0.0000

Data Index: 22885 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.6345. Min Act: -0.0000

Data Index: 686561 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.5455. Min Act: -0.0000

Data Index: 1042067 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.5131. Min Act: -0.0000

Data Index: 91932 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.6098. Min Act: -0.0000

Data Index: 1190272 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.7090. Min Act: -0.0000

Data Index: 800246 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.4992. Min Act: -0.0000

Data Index: 122477 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.4159. Min Act: -0.0000

Data Index: 1073568 (C4 (Web Text))

Max Activating Token Index: 587