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

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

Neuron 4934 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: 0.5616. Min Range: -0.5616

Max Act: 0.5490. Min Act: -0.0000

Data Index: 843082 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5616. Min Act: -0.0000

Data Index: 333740 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4725. Min Act: 0.0000

Data Index: 63637 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5249. Min Act: -0.0000

Data Index: 493325 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5212. Min Act: -0.0000

Data Index: 58933 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4957. Min Act: 0.0000

Data Index: 12381 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4518. Min Act: -0.0000

Data Index: 993267 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4703. Min Act: -0.0000

Data Index: 835175 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1752 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4927. Min Act: -0.0000

Data Index: 869801 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1151016 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4622. Min Act: -0.0000

Data Index: 505177 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4908. Min Act: -0.0000

Data Index: 752020 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4717. Min Act: -0.0000

Data Index: 107868 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4564. Min Act: -0.0000

Data Index: 482301 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1348603 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4639. Min Act: -0.0000

Data Index: 284587 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4486. Min Act: -0.0000

Data Index: 602571 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3637. Min Act: -0.0000

Data Index: 870754 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4585. Min Act: -0.0000

Data Index: 83310 (C4 (Web Text))

Max Activating Token Index: 369