Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 244 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0586. Min Act: -0.0002

Data Index: 117358 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0496. Min Act: -0.0002

Data Index: 396717 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0500. Min Act: -0.0002

Data Index: 318762 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0501. Min Act: -0.0002

Data Index: 787600 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0505. Min Act: -0.0002

Data Index: 674203 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1149701 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0478. Min Act: -0.0002

Data Index: 267956 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0468. Min Act: -0.0001

Data Index: 203468 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0475. Min Act: -0.0002

Data Index: 318656 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1176235 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0463. Min Act: -0.0002

Data Index: 247018 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1025643 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1028209 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1312758 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0459. Min Act: -0.0002

Data Index: 945419 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0439. Min Act: -0.0002

Data Index: 685507 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0438. Min Act: -0.0002

Data Index: 912864 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0423. Min Act: -0.0002

Data Index: 991597 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0441. Min Act: -0.0002

Data Index: 368763 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0430. Min Act: -0.0002

Data Index: 684970 (C4 (Web Text))

Max Activating Token Index: 864