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

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

Neuron 2015 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8772. Min Range: -2.8772

Max Act: 2.8772. Min Act: -0.0001

Data Index: 1290753 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 2.8772. Min Range: -2.8772

Max Act: 2.5665. Min Act: -0.0001

Data Index: 1222014 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 2.8772. Min Range: -2.8772

Max Act: 2.2179. Min Act: -0.0001

Data Index: 254004 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 2.8772. Min Range: -2.8772

Max Act: 2.0719. Min Act: -0.0000

Data Index: 1077113 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 2.8772. Min Range: -2.8772

Max Act: 2.0693. Min Act: -0.0001

Data Index: 941895 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 2.8772. Min Range: -2.8772

Max Act: 2.0531. Min Act: -0.0001

Data Index: 1091437 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.9327. Min Act: -0.0001

Data Index: 731049 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 2.8772. Min Range: -2.8772

Max Act: 2.0333. Min Act: -0.0001

Data Index: 524704 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.9183. Min Act: -0.0001

Data Index: 162578 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.8571. Min Act: -0.0000

Data Index: 40551 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.8686. Min Act: -0.0001

Data Index: 238829 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.9358. Min Act: -0.0000

Data Index: 1008867 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.7095. Min Act: -0.0001

Data Index: 1072876 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.8784. Min Act: -0.0000

Data Index: 282969 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.8658. Min Act: -0.0000

Data Index: 1085670 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.7667. Min Act: -0.0000

Data Index: 536607 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.7669. Min Act: -0.0000

Data Index: 24228 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.8513. Min Act: -0.0001

Data Index: 711809 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.7435. Min Act: -0.0001

Data Index: 418708 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 2.8772. Min Range: -2.8772

Max Act: 1.5538. Min Act: -0.0000

Data Index: 1076887 (C4 (Web Text))

Max Activating Token Index: 684