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

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

Neuron 6122 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1122. Min Range: -1.1122

Max Act: 1.1122. Min Act: -0.0001

Data Index: 1284995 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.1122. Min Range: -1.1122

Max Act: 1.0242. Min Act: -0.0000

Data Index: 574209 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8260. Min Act: -0.0001

Data Index: 718210 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1220545 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6979. Min Act: -0.0000

Data Index: 463212 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1306660 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1204930 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6639. Min Act: -0.0001

Data Index: 471133 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6765. Min Act: -0.0000

Data Index: 855181 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1342399 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.7358. Min Act: -0.0000

Data Index: 992545 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6617. Min Act: -0.0000

Data Index: 904012 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6672. Min Act: -0.0000

Data Index: 530899 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6566. Min Act: -0.0000

Data Index: 75130 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1149668 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6907. Min Act: -0.0000

Data Index: 778151 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1590278 (Python Code)

Max Activating Token Index: 350

Text #18

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1343762 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.5834. Min Act: -0.0001

Data Index: 1327611 (C4 (Web Text))

Max Activating Token Index: 861