Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3915 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.1598. Min Act: -0.0000

Data Index: 905698 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0588. Min Act: -0.0001

Data Index: 162763 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1015437 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0251. Min Act: -0.0001

Data Index: 708860 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9645. Min Act: -0.0000

Data Index: 55451 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9564. Min Act: -0.0000

Data Index: 327989 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9557. Min Act: -0.0000

Data Index: 497702 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9526. Min Act: -0.0001

Data Index: 928014 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9758. Min Act: -0.0001

Data Index: 703589 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9394. Min Act: -0.0001

Data Index: 698467 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9727. Min Act: -0.0000

Data Index: 567851 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1100899 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9312. Min Act: -0.0000

Data Index: 993497 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9272. Min Act: -0.0000

Data Index: 566475 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9222. Min Act: -0.0000

Data Index: 264896 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9193. Min Act: -0.0001

Data Index: 638693 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8905. Min Act: -0.0000

Data Index: 315501 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8902. Min Act: -0.0000

Data Index: 1255717 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9726. Min Act: -0.0001

Data Index: 875775 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9127. Min Act: -0.0000

Data Index: 36840 (C4 (Web Text))

Max Activating Token Index: 402