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

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

Neuron 3049 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: 1.3018. Min Range: -1.3018

Max Act: 1.3018. Min Act: -0.0000

Data Index: 839576 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.2504. Min Act: -0.0000

Data Index: 557268 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.0978. Min Act: -0.0000

Data Index: 193030 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1232989 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.0413. Min Act: -0.0000

Data Index: 764700 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.0551. Min Act: -0.0000

Data Index: 249066 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.0296. Min Act: -0.0000

Data Index: 527800 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.9895. Min Act: -0.0000

Data Index: 9365 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.0151. Min Act: -0.0000

Data Index: 23260 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.0046. Min Act: -0.0000

Data Index: 15622 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.9521. Min Act: -0.0000

Data Index: 855399 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.9379. Min Act: -0.0000

Data Index: 205301 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.9185. Min Act: -0.0000

Data Index: 6464 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1004251 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.9373. Min Act: -0.0000

Data Index: 95814 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8784. Min Act: -0.0000

Data Index: 779141 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8752. Min Act: -0.0000

Data Index: 574899 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8595. Min Act: -0.0000

Data Index: 188568 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.9284. Min Act: -0.0000

Data Index: 758329 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1092643 (C4 (Web Text))

Max Activating Token Index: 431