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

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

Neuron 1008 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4498. Min Range: -8.4498

Max Act: 8.4498. Min Act: -0.0000

Data Index: 1307874 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 8.4498. Min Range: -8.4498

Max Act: 8.1764. Min Act: -0.0000

Data Index: 319764 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.8787. Min Act: -0.0000

Data Index: 993778 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 8.4498. Min Range: -8.4498

Max Act: 8.1966. Min Act: -0.0000

Data Index: 644053 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 8.4498. Min Range: -8.4498

Max Act: 8.0279. Min Act: -0.0000

Data Index: 515166 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.6446. Min Act: -0.0000

Data Index: 183954 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.6636. Min Act: -0.0000

Data Index: 826334 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.5757. Min Act: -0.0000

Data Index: 1173568 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.5244. Min Act: -0.0000

Data Index: 469352 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.3544. Min Act: -0.0000

Data Index: 1059089 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.4923. Min Act: -0.0000

Data Index: 410651 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.3423. Min Act: -0.0000

Data Index: 664636 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.6652. Min Act: -0.0000

Data Index: 628121 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.1335. Min Act: -0.0000

Data Index: 1100532 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.1639. Min Act: -0.0000

Data Index: 450821 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.2984. Min Act: -0.0000

Data Index: 1011330 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.2705. Min Act: -0.0000

Data Index: 544263 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.3086. Min Act: -0.0000

Data Index: 350005 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.2858. Min Act: -0.0000

Data Index: 793764 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 8.4498. Min Range: -8.4498

Max Act: 7.4438. Min Act: -0.0000

Data Index: 638646 (C4 (Web Text))

Max Activating Token Index: 442