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

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

Neuron 3877 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: 2.9911. Min Range: -2.9911

Max Act: 2.9911. Min Act: -0.0000

Data Index: 1341700 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.7874. Min Act: -0.0000

Data Index: 33693 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.4352. Min Act: -0.0000

Data Index: 247325 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.4662. Min Act: -0.0000

Data Index: 405307 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.4324. Min Act: -0.0000

Data Index: 602603 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.5229. Min Act: -0.0000

Data Index: 181512 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.3558. Min Act: -0.0000

Data Index: 966522 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.4681. Min Act: -0.0000

Data Index: 66679 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.4332. Min Act: -0.0000

Data Index: 1006242 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.5542. Min Act: -0.0000

Data Index: 931197 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.5278. Min Act: -0.0000

Data Index: 163140 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.1467. Min Act: -0.0000

Data Index: 229194 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.5491. Min Act: -0.0000

Data Index: 808280 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.3849. Min Act: -0.0000

Data Index: 346132 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.4939. Min Act: -0.0000

Data Index: 793036 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.4923. Min Act: -0.0000

Data Index: 822928 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.3773. Min Act: -0.0000

Data Index: 709131 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.5128. Min Act: -0.0000

Data Index: 1054362 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.4699. Min Act: -0.0000

Data Index: 46230 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 2.9911. Min Range: -2.9911

Max Act: 2.4471. Min Act: -0.0000

Data Index: 1224115 (C4 (Web Text))

Max Activating Token Index: 56