Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2507 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2742. Min Range: -1.2742

Max Act: 1.2742. Min Act: 0.0000

Data Index: 1394783 (Python Code)

Max Activating Token Index: 149

Text #1

Max Range: 1.2742. Min Range: -1.2742

Max Act: 1.2145. Min Act: 0.0000

Data Index: 1514317 (Python Code)

Max Activating Token Index: 760

Text #2

Max Range: 1.2742. Min Range: -1.2742

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1488942 (Python Code)

Max Activating Token Index: 332

Text #3

Max Range: 1.2742. Min Range: -1.2742

Max Act: 1.0652. Min Act: -0.0000

Data Index: 34545 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 1.2742. Min Range: -1.2742

Max Act: 1.0356. Min Act: -0.0000

Data Index: 978476 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1389994 (Python Code)

Max Activating Token Index: 854

Text #6

Max Range: 1.2742. Min Range: -1.2742

Max Act: 1.0110. Min Act: -0.0000

Data Index: 1134652 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.9535. Min Act: -0.0000

Data Index: 617037 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1594968 (Python Code)

Max Activating Token Index: 817

Text #9

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.8629. Min Act: -0.0000

Data Index: 527831 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.8517. Min Act: -0.0000

Data Index: 959177 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.8924. Min Act: -0.0000

Data Index: 819707 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.8904. Min Act: -0.0000

Data Index: 252376 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.7836. Min Act: -0.0000

Data Index: 800787 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1386632 (Python Code)

Max Activating Token Index: 658

Text #15

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1111026 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.8293. Min Act: -0.0000

Data Index: 462013 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1410298 (Python Code)

Max Activating Token Index: 532

Text #18

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.7822. Min Act: -0.0000

Data Index: 46093 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 1.2742. Min Range: -1.2742

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1149929 (C4 (Web Text))

Max Activating Token Index: 827