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

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

Neuron 5000 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: 2.3028. Min Range: -2.3028

Max Act: 2.3028. Min Act: -0.0000

Data Index: 84609 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.8686. Min Act: -0.0000

Data Index: 1317165 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.6350. Min Act: -0.0000

Data Index: 1154220 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.8630. Min Act: -0.0000

Data Index: 183302 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.7457. Min Act: -0.0000

Data Index: 1325584 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.7154. Min Act: -0.0000

Data Index: 889712 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.6640. Min Act: -0.0000

Data Index: 165130 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.6158. Min Act: -0.0000

Data Index: 478653 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.6507. Min Act: -0.0000

Data Index: 259601 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.7481. Min Act: -0.0000

Data Index: 1317643 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.7984. Min Act: -0.0000

Data Index: 758429 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.4954. Min Act: -0.0000

Data Index: 487244 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.7374. Min Act: -0.0000

Data Index: 1109823 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.4973. Min Act: -0.0000

Data Index: 1095795 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.5878. Min Act: -0.0000

Data Index: 973479 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.4926. Min Act: -0.0000

Data Index: 1276614 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.5888. Min Act: -0.0000

Data Index: 8483 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.6107. Min Act: -0.0000

Data Index: 1000730 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.6011. Min Act: -0.0000

Data Index: 963509 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 2.3028. Min Range: -2.3028

Max Act: 1.5067. Min Act: -0.0000

Data Index: 1077424 (C4 (Web Text))

Max Activating Token Index: 182