Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2372 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0888. Min Range: -2.0888

Max Act: 2.0888. Min Act: -0.0000

Data Index: 1334629 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.8488. Min Act: -0.0001

Data Index: 1357763 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 2.0888. Min Range: -2.0888

Max Act: 2.0790. Min Act: -0.0000

Data Index: 922003 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.9061. Min Act: -0.0001

Data Index: 187109 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.8970. Min Act: -0.0000

Data Index: 303788 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.8405. Min Act: -0.0000

Data Index: 629852 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.9117. Min Act: -0.0001

Data Index: 603278 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.8465. Min Act: -0.0000

Data Index: 1346777 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.8183. Min Act: -0.0001

Data Index: 55095 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.7501. Min Act: -0.0000

Data Index: 437231 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.6466. Min Act: -0.0000

Data Index: 1074965 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.7767. Min Act: -0.0000

Data Index: 651460 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.6615. Min Act: -0.0001

Data Index: 1100529 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.7355. Min Act: -0.0000

Data Index: 569340 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.5744. Min Act: -0.0001

Data Index: 1230645 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.5112. Min Act: -0.0000

Data Index: 796882 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.4276. Min Act: -0.0001

Data Index: 584857 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.6126. Min Act: -0.0001

Data Index: 149603 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.6025. Min Act: -0.0001

Data Index: 1103582 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 2.0888. Min Range: -2.0888

Max Act: 1.4968. Min Act: -0.0000

Data Index: 1097094 (C4 (Web Text))

Max Activating Token Index: 812