Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5141 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1006143 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1081868 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1026671 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4904. Min Act: -0.0000

Data Index: 924754 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4287. Min Act: -0.0000

Data Index: 250069 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4149. Min Act: 0.0001

Data Index: 495400 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4123. Min Act: -0.0000

Data Index: 603805 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3941. Min Act: -0.0000

Data Index: 250577 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3692. Min Act: -0.0000

Data Index: 551414 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1982 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3746. Min Act: -0.0000

Data Index: 828715 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3753. Min Act: -0.0000

Data Index: 921816 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3568. Min Act: -0.0000

Data Index: 700729 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3568. Min Act: 0.0001

Data Index: 1187177 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3738. Min Act: -0.0000

Data Index: 511952 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3560. Min Act: -0.0000

Data Index: 928938 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1318368 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3448. Min Act: -0.0000

Data Index: 953681 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3446. Min Act: -0.0000

Data Index: 223010 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.3336. Min Act: 0.0000

Data Index: 328392 (C4 (Web Text))

Max Activating Token Index: 1021