Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1360 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0479. Min Act: -0.0003

Data Index: 67445 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0467. Min Act: -0.0003

Data Index: 500710 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0459. Min Act: -0.0003

Data Index: 390157 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0445. Min Act: -0.0003

Data Index: 579902 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0429. Min Act: -0.0003

Data Index: 866847 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1072742 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1173192 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0003

Data Index: 167312 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0447. Min Act: -0.0003

Data Index: 484614 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0423. Min Act: -0.0003

Data Index: 246005 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0409. Min Act: -0.0003

Data Index: 542860 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0434. Min Act: -0.0003

Data Index: 797261 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1032702 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0417. Min Act: -0.0003

Data Index: 622819 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0408. Min Act: -0.0003

Data Index: 424917 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0395. Min Act: -0.0003

Data Index: 37501 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0409. Min Act: -0.0003

Data Index: 185348 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0388. Min Act: -0.0003

Data Index: 796355 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0388. Min Act: -0.0003

Data Index: 888302 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0402. Min Act: -0.0003

Data Index: 595134 (C4 (Web Text))

Max Activating Token Index: 398