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

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

Neuron 2822 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3611. Min Range: -2.3611

Max Act: 2.2919. Min Act: -0.0000

Data Index: 1654865 (Python Code)

Max Activating Token Index: 870

Text #1

Max Range: 2.3611. Min Range: -2.3611

Max Act: 2.2592. Min Act: -0.0000

Data Index: 1642309 (Python Code)

Max Activating Token Index: 550

Text #2

Max Range: 2.3611. Min Range: -2.3611

Max Act: 2.3611. Min Act: -0.0000

Data Index: 43996 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.9105. Min Act: -0.0000

Data Index: 141372 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.7220. Min Act: -0.0000

Data Index: 1564877 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.8044. Min Act: -0.0000

Data Index: 1302640 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.8829. Min Act: -0.0000

Data Index: 1641226 (Python Code)

Max Activating Token Index: 892

Text #7

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.6866. Min Act: -0.0000

Data Index: 1129860 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.9383. Min Act: -0.0000

Data Index: 1484711 (Python Code)

Max Activating Token Index: 576

Text #9

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.9585. Min Act: -0.0000

Data Index: 1441321 (Python Code)

Max Activating Token Index: 697

Text #10

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.8226. Min Act: -0.0000

Data Index: 1620496 (Python Code)

Max Activating Token Index: 834

Text #11

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.7115. Min Act: -0.0000

Data Index: 1392596 (Python Code)

Max Activating Token Index: 496

Text #12

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.4356. Min Act: -0.0000

Data Index: 1412576 (Python Code)

Max Activating Token Index: 266

Text #13

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.6271. Min Act: -0.0000

Data Index: 1606037 (Python Code)

Max Activating Token Index: 418

Text #14

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.7063. Min Act: -0.0000

Data Index: 1415151 (Python Code)

Max Activating Token Index: 875

Text #15

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.6466. Min Act: -0.0000

Data Index: 1444791 (Python Code)

Max Activating Token Index: 775

Text #16

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.5945. Min Act: -0.0000

Data Index: 1580053 (Python Code)

Max Activating Token Index: 806

Text #17

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.4254. Min Act: -0.0001

Data Index: 1609362 (Python Code)

Max Activating Token Index: 211

Text #18

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1376661 (Python Code)

Max Activating Token Index: 616

Text #19

Max Range: 2.3611. Min Range: -2.3611

Max Act: 1.6327. Min Act: -0.0000

Data Index: 1651871 (Python Code)

Max Activating Token Index: 255