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

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

Neuron 3547 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0009. Min Act: -0.0000

Data Index: 638526 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0645. Min Act: -0.0000

Data Index: 663997 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9719. Min Act: -0.0000

Data Index: 534461 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1269863 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9953. Min Act: -0.0000

Data Index: 641476 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9371. Min Act: -0.0000

Data Index: 297441 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9305. Min Act: -0.0000

Data Index: 575971 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9206. Min Act: -0.0000

Data Index: 320146 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8587. Min Act: -0.0000

Data Index: 153314 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8911. Min Act: -0.0000

Data Index: 252804 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1011139 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9396. Min Act: -0.0000

Data Index: 774227 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8831. Min Act: -0.0000

Data Index: 777089 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8589. Min Act: -0.0000

Data Index: 981136 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0250. Min Act: -0.0000

Data Index: 651444 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8528. Min Act: -0.0000

Data Index: 902155 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8534. Min Act: -0.0000

Data Index: 550824 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9194. Min Act: -0.0000

Data Index: 651369 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1240574 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8300. Min Act: -0.0000

Data Index: 265729 (C4 (Web Text))

Max Activating Token Index: 314