Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2885 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1336789 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.5413. Min Act: -0.0001

Data Index: 62322 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.5266. Min Act: -0.0001

Data Index: 208351 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4907. Min Act: -0.0001

Data Index: 1329976 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4718. Min Act: -0.0001

Data Index: 459177 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4869. Min Act: -0.0001

Data Index: 415136 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4430. Min Act: -0.0001

Data Index: 720329 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4646. Min Act: -0.0001

Data Index: 78468 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4422. Min Act: -0.0001

Data Index: 382676 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4574. Min Act: -0.0000

Data Index: 448196 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4159. Min Act: -0.0001

Data Index: 594983 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4195. Min Act: -0.0001

Data Index: 987972 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4153. Min Act: -0.0000

Data Index: 905048 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3774. Min Act: -0.0001

Data Index: 212531 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3882. Min Act: -0.0001

Data Index: 139276 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3895. Min Act: -0.0000

Data Index: 556517 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3947. Min Act: -0.0001

Data Index: 7223 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3816. Min Act: -0.0000

Data Index: 633965 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3322. Min Act: -0.0001

Data Index: 1265 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3944. Min Act: -0.0001

Data Index: 463923 (C4 (Web Text))

Max Activating Token Index: 695