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

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

Neuron 1747 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: 2.3740. Min Range: -2.3740

Max Act: 2.3740. Min Act: -0.0000

Data Index: 173513 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 2.3740. Min Range: -2.3740

Max Act: 2.0153. Min Act: -0.0000

Data Index: 1333816 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.6900. Min Act: -0.0000

Data Index: 419174 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.7030. Min Act: -0.0000

Data Index: 340781 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.5867. Min Act: -0.0000

Data Index: 487635 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.5479. Min Act: -0.0000

Data Index: 1143055 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.4711. Min Act: -0.0000

Data Index: 946834 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.5250. Min Act: -0.0000

Data Index: 1024043 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.3726. Min Act: -0.0000

Data Index: 686898 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.4934. Min Act: -0.0000

Data Index: 582774 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.4558. Min Act: -0.0000

Data Index: 590833 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.4977. Min Act: -0.0000

Data Index: 937484 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.4049. Min Act: -0.0000

Data Index: 128479 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.4390. Min Act: -0.0000

Data Index: 958849 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.4340. Min Act: -0.0000

Data Index: 1230172 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.4299. Min Act: -0.0000

Data Index: 711748 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.4635. Min Act: -0.0000

Data Index: 354875 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.4581. Min Act: -0.0000

Data Index: 270339 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1288255 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 2.3740. Min Range: -2.3740

Max Act: 1.3643. Min Act: -0.0000

Data Index: 775680 (C4 (Web Text))

Max Activating Token Index: 197