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

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

Neuron 1117 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.6479. Min Act: -0.0000

Data Index: 928205 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5969. Min Act: -0.0000

Data Index: 731623 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5528. Min Act: -0.0000

Data Index: 639876 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5484. Min Act: -0.0000

Data Index: 162158 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1149864 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5577. Min Act: -0.0000

Data Index: 430925 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5169. Min Act: -0.0000

Data Index: 738532 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5510. Min Act: -0.0000

Data Index: 992143 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4857. Min Act: -0.0000

Data Index: 95161 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1203388 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5061. Min Act: -0.0000

Data Index: 601899 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5022. Min Act: -0.0000

Data Index: 443531 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1116840 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1261908 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4932. Min Act: -0.0000

Data Index: 729698 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1184917 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4913. Min Act: -0.0000

Data Index: 207410 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4684. Min Act: -0.0000

Data Index: 292601 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4838. Min Act: -0.0000

Data Index: 348201 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4798. Min Act: -0.0000

Data Index: 183650 (C4 (Web Text))

Max Activating Token Index: 113