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

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

Neuron 4697 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3583. Min Act: -0.0000

Data Index: 249849 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1015014 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3613. Min Act: -0.0000

Data Index: 853059 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3337. Min Act: -0.0000

Data Index: 514136 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3419. Min Act: -0.0000

Data Index: 187558 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3255. Min Act: -0.0000

Data Index: 160361 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3133. Min Act: -0.0000

Data Index: 233067 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3131. Min Act: -0.0000

Data Index: 689484 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3115. Min Act: -0.0000

Data Index: 837035 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3076. Min Act: -0.0000

Data Index: 856140 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1182093 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1128779 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3136. Min Act: -0.0000

Data Index: 641424 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2954. Min Act: -0.0000

Data Index: 205264 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2944. Min Act: -0.0000

Data Index: 556301 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2940. Min Act: -0.0000

Data Index: 156414 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2881. Min Act: -0.0000

Data Index: 585441 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1127174 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2936. Min Act: -0.0000

Data Index: 913578 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2914. Min Act: -0.0000

Data Index: 264596 (C4 (Web Text))

Max Activating Token Index: 384