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

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

Neuron 3228 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.5001. Min Act: -0.0000

Data Index: 160383 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.4148. Min Act: -0.0000

Data Index: 59529 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1123447 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.3091. Min Act: -0.0000

Data Index: 1323162 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.3063. Min Act: -0.0000

Data Index: 765228 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.2228. Min Act: -0.0000

Data Index: 496126 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.2478. Min Act: -0.0000

Data Index: 488239 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.2300. Min Act: -0.0000

Data Index: 617417 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1633. Min Act: -0.0000

Data Index: 29648 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.2177. Min Act: -0.0000

Data Index: 1289123 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1235790 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1148. Min Act: -0.0000

Data Index: 669285 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1753. Min Act: -0.0000

Data Index: 685133 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1664. Min Act: -0.0000

Data Index: 1532325 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1305052 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1275714 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1330. Min Act: -0.0000

Data Index: 1394405 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.2001. Min Act: -0.0000

Data Index: 468193 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.0635. Min Act: -0.0000

Data Index: 843683 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 1.5001. Min Range: -1.5001

Max Act: 1.1755. Min Act: -0.0000

Data Index: 734888 (C4 (Web Text))

Max Activating Token Index: 136