Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2548 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0000

Data Index: 364217 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0514. Min Act: -0.0000

Data Index: 45882 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1193793 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1298674 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0442. Min Act: -0.0000

Data Index: 832714 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1056363 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1048856 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0438. Min Act: -0.0000

Data Index: 463493 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0423. Min Act: -0.0000

Data Index: 1540673 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0454. Min Act: -0.0000

Data Index: 825107 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0414. Min Act: -0.0000

Data Index: 596874 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0414. Min Act: -0.0000

Data Index: 498434 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0413. Min Act: -0.0000

Data Index: 1433510 (Python Code)

Max Activating Token Index: 819

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0421. Min Act: -0.0000

Data Index: 62205 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0391. Min Act: -0.0000

Data Index: 1631119 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0389. Min Act: -0.0000

Data Index: 472867 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0383. Min Act: -0.0000

Data Index: 952006 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1439262 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0361. Min Act: -0.0000

Data Index: 1209905 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0385. Min Act: -0.0000

Data Index: 445991 (C4 (Web Text))

Max Activating Token Index: 463