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

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

Neuron 3307 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3674. Min Act: -0.0001

Data Index: 501601 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3666. Min Act: -0.0001

Data Index: 972719 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3630. Min Act: -0.0001

Data Index: 1110240 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3607. Min Act: -0.0002

Data Index: 1273187 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3591. Min Act: -0.0001

Data Index: 445829 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3233. Min Act: -0.0001

Data Index: 250884 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3263. Min Act: -0.0001

Data Index: 1188686 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3266. Min Act: -0.0001

Data Index: 657752 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3016. Min Act: -0.0001

Data Index: 370889 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3381. Min Act: -0.0001

Data Index: 529813 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3161. Min Act: -0.0001

Data Index: 1548550 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3159. Min Act: -0.0001

Data Index: 167592 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3272. Min Act: -0.0001

Data Index: 1155514 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3095. Min Act: -0.0001

Data Index: 918700 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2911. Min Act: -0.0001

Data Index: 221770 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3111. Min Act: -0.0001

Data Index: 353698 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3093. Min Act: -0.0001

Data Index: 481971 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3274. Min Act: -0.0001

Data Index: 717781 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2913. Min Act: -0.0001

Data Index: 683674 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2897. Min Act: -0.0001

Data Index: 983596 (C4 (Web Text))

Max Activating Token Index: 385