Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1116 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3480. Min Range: -2.3480

Max Act: 2.3042. Min Act: 0.0000

Data Index: 363536 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 2.3480. Min Range: -2.3480

Max Act: 2.3480. Min Act: -0.0000

Data Index: 67311 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 2.3480. Min Range: -2.3480

Max Act: 2.0631. Min Act: -0.0000

Data Index: 1056493 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.9562. Min Act: -0.0000

Data Index: 1247783 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.8578. Min Act: -0.0000

Data Index: 65185 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.8526. Min Act: -0.0000

Data Index: 478611 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.8443. Min Act: -0.0000

Data Index: 724279 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.8240. Min Act: -0.0000

Data Index: 895874 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.8050. Min Act: -0.0000

Data Index: 1294730 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.7567. Min Act: -0.0000

Data Index: 398118 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.6498. Min Act: -0.0000

Data Index: 458442 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.7474. Min Act: -0.0000

Data Index: 1323506 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.6474. Min Act: -0.0000

Data Index: 30455 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.7098. Min Act: -0.0000

Data Index: 1157135 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.6914. Min Act: -0.0000

Data Index: 783103 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.6320. Min Act: -0.0000

Data Index: 780243 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.5911. Min Act: -0.0000

Data Index: 859185 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.4826. Min Act: -0.0000

Data Index: 1134268 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.5617. Min Act: -0.0000

Data Index: 351947 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 2.3480. Min Range: -2.3480

Max Act: 1.5323. Min Act: 0.0000

Data Index: 1052971 (C4 (Web Text))

Max Activating Token Index: 834