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

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

Neuron 326 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.4158. Min Act: -0.0000

Data Index: 997343 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3063. Min Act: -0.0000

Data Index: 192228 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3129. Min Act: -0.0000

Data Index: 708096 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1073071 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1265088 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2950. Min Act: -0.0000

Data Index: 132214 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2936. Min Act: -0.0000

Data Index: 829527 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.3094. Min Act: -0.0000

Data Index: 359356 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2685. Min Act: -0.0000

Data Index: 292168 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1261128 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2790. Min Act: -0.0000

Data Index: 274017 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2661. Min Act: -0.0000

Data Index: 411457 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2924. Min Act: -0.0000

Data Index: 80651 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1302033 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2608. Min Act: -0.0000

Data Index: 497615 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2646. Min Act: -0.0000

Data Index: 245270 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2768. Min Act: -0.0000

Data Index: 695169 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2825. Min Act: -0.0000

Data Index: 1169702 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2649. Min Act: -0.0000

Data Index: 136145 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.4158. Min Range: -0.4158

Max Act: 0.2534. Min Act: -0.0000

Data Index: 750618 (C4 (Web Text))

Max Activating Token Index: 695