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

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

Neuron 3422 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 581950 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0757. Min Act: -0.0002

Data Index: 168415 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0727. Min Act: -0.0002

Data Index: 692157 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0700. Min Act: -0.0002

Data Index: 343431 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1253435 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1339462 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0670. Min Act: -0.0002

Data Index: 196317 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0665. Min Act: -0.0002

Data Index: 768719 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0667. Min Act: -0.0002

Data Index: 543747 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0643. Min Act: -0.0002

Data Index: 22528 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1142282 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1095206 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0622. Min Act: -0.0002

Data Index: 20485 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1237445 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0616. Min Act: -0.0002

Data Index: 538728 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0617. Min Act: -0.0002

Data Index: 299900 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1327388 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0614. Min Act: -0.0002

Data Index: 903607 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0605. Min Act: -0.0002

Data Index: 420392 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0649. Min Act: -0.0002

Data Index: 850724 (C4 (Web Text))

Max Activating Token Index: 274