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

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

Neuron 4063 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2659. Min Act: -0.0001

Data Index: 533153 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2480. Min Act: -0.0001

Data Index: 411196 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2562. Min Act: -0.0001

Data Index: 928430 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2361. Min Act: -0.0001

Data Index: 269277 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1120412 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2117. Min Act: -0.0002

Data Index: 1318133 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1995. Min Act: -0.0001

Data Index: 534372 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2084. Min Act: -0.0002

Data Index: 72850 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1726. Min Act: -0.0001

Data Index: 776136 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1832. Min Act: -0.0001

Data Index: 700141 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1710. Min Act: -0.0001

Data Index: 524608 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1852. Min Act: -0.0001

Data Index: 233877 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1634. Min Act: -0.0001

Data Index: 363757 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1446583 (Python Code)

Max Activating Token Index: 43

Text #14

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1493. Min Act: -0.0001

Data Index: 871897 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1661. Min Act: -0.0001

Data Index: 685284 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1191032 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1081734 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1530. Min Act: -0.0001

Data Index: 766804 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1443. Min Act: -0.0001

Data Index: 156294 (C4 (Web Text))

Max Activating Token Index: 499