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

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

Neuron 1431 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: 0.0527. Min Range: -0.0527

Max Act: 0.0524. Min Act: -0.0004

Data Index: 268171 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1034544 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0478. Min Act: -0.0003

Data Index: 909311 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0469. Min Act: -0.0003

Data Index: 670385 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1116769 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0456. Min Act: -0.0004

Data Index: 1258173 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1172444 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0451. Min Act: -0.0003

Data Index: 130015 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0432. Min Act: -0.0003

Data Index: 83533 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0412. Min Act: -0.0003

Data Index: 374116 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0410. Min Act: -0.0003

Data Index: 790632 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0411. Min Act: -0.0004

Data Index: 344681 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0411. Min Act: -0.0003

Data Index: 378463 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0395. Min Act: -0.0003

Data Index: 512513 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0402. Min Act: -0.0003

Data Index: 1067985 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0392. Min Act: -0.0003

Data Index: 671890 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1029723 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0394. Min Act: -0.0003

Data Index: 468869 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0394. Min Act: -0.0003

Data Index: 57429 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1303034 (C4 (Web Text))

Max Activating Token Index: 445