Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1471 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1249438 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0493. Min Act: -0.0003

Data Index: 289840 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0473. Min Act: -0.0003

Data Index: 642889 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0440. Min Act: -0.0003

Data Index: 837852 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0432. Min Act: -0.0003

Data Index: 357433 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0443. Min Act: -0.0004

Data Index: 337656 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0441. Min Act: -0.0002

Data Index: 246213 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0407. Min Act: -0.0003

Data Index: 278325 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0435. Min Act: -0.0003

Data Index: 139043 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0440. Min Act: -0.0004

Data Index: 1271077 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0418. Min Act: -0.0004

Data Index: 1159330 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0390. Min Act: -0.0003

Data Index: 310058 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0429. Min Act: -0.0003

Data Index: 467791 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0397. Min Act: -0.0003

Data Index: 627367 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0416. Min Act: -0.0003

Data Index: 299598 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1007780 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1876 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0378. Min Act: -0.0003

Data Index: 417884 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1317183 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0344. Min Act: -0.0003

Data Index: 629216 (C4 (Web Text))

Max Activating Token Index: 783