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

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

Neuron 2060 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2338. Min Act: -0.0001

Data Index: 691066 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1967. Min Act: -0.0000

Data Index: 682639 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1933. Min Act: -0.0001

Data Index: 691764 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2064. Min Act: -0.0001

Data Index: 750533 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1724. Min Act: -0.0001

Data Index: 468407 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1848. Min Act: -0.0001

Data Index: 260305 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1956. Min Act: -0.0001

Data Index: 502778 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1925. Min Act: -0.0001

Data Index: 512409 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1860. Min Act: -0.0001

Data Index: 713910 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1601. Min Act: -0.0001

Data Index: 664892 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1753. Min Act: -0.0000

Data Index: 415947 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1693. Min Act: -0.0000

Data Index: 376547 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1582. Min Act: -0.0000

Data Index: 332303 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1743. Min Act: -0.0001

Data Index: 108882 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1663. Min Act: -0.0000

Data Index: 95591 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1628. Min Act: -0.0001

Data Index: 554090 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1085076 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1178795 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1614. Min Act: -0.0000

Data Index: 870360 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1481. Min Act: -0.0000

Data Index: 64710 (C4 (Web Text))

Max Activating Token Index: 588