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

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

Neuron 4844 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3664. Min Range: -2.3664

Max Act: 2.3664. Min Act: -0.0000

Data Index: 562221 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 2.3664. Min Range: -2.3664

Max Act: 2.1215. Min Act: -0.0000

Data Index: 78695 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.8142. Min Act: -0.0000

Data Index: 1080547 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.9779. Min Act: -0.0000

Data Index: 910533 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.8485. Min Act: -0.0000

Data Index: 690304 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.7460. Min Act: -0.0000

Data Index: 795543 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.5823. Min Act: -0.0000

Data Index: 983502 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.5731. Min Act: -0.0000

Data Index: 1295052 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.5677. Min Act: -0.0000

Data Index: 241357 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.4563. Min Act: -0.0000

Data Index: 19351 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.4535. Min Act: -0.0000

Data Index: 634952 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.5395. Min Act: -0.0000

Data Index: 865572 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.4185. Min Act: -0.0000

Data Index: 261377 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.4893. Min Act: -0.0000

Data Index: 585184 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.4875. Min Act: -0.0000

Data Index: 256955 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.4034. Min Act: -0.0000

Data Index: 447624 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.3690. Min Act: -0.0000

Data Index: 133616 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.4512. Min Act: -0.0000

Data Index: 1283661 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.4590. Min Act: -0.0000

Data Index: 586600 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 2.3664. Min Range: -2.3664

Max Act: 1.4399. Min Act: -0.0000

Data Index: 1101883 (C4 (Web Text))

Max Activating Token Index: 465