Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 480 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0468. Min Act: -0.0001

Data Index: 4927 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0002

Data Index: 927460 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0448. Min Act: -0.0001

Data Index: 916602 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1446045 (Python Code)

Max Activating Token Index: 616

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0473. Min Act: -0.0002

Data Index: 417725 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1105681 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0424. Min Act: -0.0001

Data Index: 709696 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0404. Min Act: -0.0002

Data Index: 352719 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1170378 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1006355 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0411. Min Act: -0.0001

Data Index: 90774 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1275028 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0399. Min Act: -0.0001

Data Index: 990699 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0389. Min Act: -0.0001

Data Index: 962477 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1086165 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0377. Min Act: -0.0002

Data Index: 594577 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0401. Min Act: -0.0002

Data Index: 814 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1500692 (Python Code)

Max Activating Token Index: 750

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1267604 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0408. Min Act: -0.0002

Data Index: 395403 (C4 (Web Text))

Max Activating Token Index: 748