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

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

Neuron 535 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7984. Min Act: -0.0002

Data Index: 726732 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7670. Min Act: -0.0002

Data Index: 1265814 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7593. Min Act: -0.0002

Data Index: 808788 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7554. Min Act: -0.0002

Data Index: 651723 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7620. Min Act: -0.0002

Data Index: 863072 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7564. Min Act: -0.0002

Data Index: 190137 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7372. Min Act: -0.0002

Data Index: 1209831 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7327. Min Act: -0.0002

Data Index: 914898 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7067. Min Act: -0.0002

Data Index: 371201 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6933. Min Act: -0.0002

Data Index: 849427 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.7078. Min Act: -0.0002

Data Index: 507375 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6919. Min Act: -0.0002

Data Index: 179865 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6797. Min Act: -0.0002

Data Index: 818236 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6813. Min Act: -0.0002

Data Index: 498555 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6927. Min Act: -0.0002

Data Index: 131750 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6625. Min Act: -0.0002

Data Index: 698268 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6711. Min Act: -0.0002

Data Index: 774323 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6777. Min Act: -0.0002

Data Index: 119468 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6492. Min Act: -0.0002

Data Index: 62919 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.7984. Min Range: -0.7984

Max Act: 0.6524. Min Act: -0.0002

Data Index: 490026 (C4 (Web Text))

Max Activating Token Index: 673