Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1161 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0518. Min Act: -0.0003

Data Index: 166188 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1235824 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0452. Min Act: -0.0003

Data Index: 408645 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0437. Min Act: -0.0003

Data Index: 867966 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1021249 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0424. Min Act: -0.0003

Data Index: 654200 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0438. Min Act: -0.0003

Data Index: 725227 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1109590 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0447. Min Act: -0.0003

Data Index: 494423 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0426. Min Act: -0.0003

Data Index: 642751 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0398. Min Act: -0.0003

Data Index: 703474 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0427. Min Act: -0.0003

Data Index: 10036 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0360. Min Act: -0.0003

Data Index: 475160 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0405. Min Act: -0.0003

Data Index: 830966 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1036115 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0412. Min Act: -0.0003

Data Index: 831223 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0382. Min Act: -0.0003

Data Index: 879331 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0408. Min Act: -0.0003

Data Index: 700053 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0362. Min Act: -0.0003

Data Index: 747745 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0372. Min Act: -0.0003

Data Index: 830050 (C4 (Web Text))

Max Activating Token Index: 860