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

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

Neuron 14 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.5021. Min Act: -0.0000

Data Index: 528016 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4788. Min Act: -0.0000

Data Index: 784799 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4361. Min Act: -0.0000

Data Index: 341020 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4387. Min Act: -0.0000

Data Index: 311513 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4559. Min Act: -0.0000

Data Index: 918142 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1028553 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4319. Min Act: -0.0000

Data Index: 161260 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4260. Min Act: -0.0000

Data Index: 389492 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3970. Min Act: -0.0000

Data Index: 551561 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4166. Min Act: -0.0000

Data Index: 904018 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3795. Min Act: -0.0000

Data Index: 773947 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4043. Min Act: -0.0000

Data Index: 736372 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3995. Min Act: -0.0000

Data Index: 677718 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3817. Min Act: 0.0000

Data Index: 620417 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3843. Min Act: 0.0000

Data Index: 485732 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3566. Min Act: -0.0000

Data Index: 853622 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3669. Min Act: -0.0000

Data Index: 804223 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3651. Min Act: -0.0000

Data Index: 433779 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1097648 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3490. Min Act: 0.0000

Data Index: 884435 (C4 (Web Text))

Max Activating Token Index: 524