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

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

Neuron 2323 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6998. Min Range: -1.6998

Max Act: 1.6998. Min Act: -0.0003

Data Index: 1349942 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 1.6998. Min Range: -1.6998

Max Act: 1.4871. Min Act: -0.0003

Data Index: 1345280 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 1.6998. Min Range: -1.6998

Max Act: 1.2161. Min Act: -0.0003

Data Index: 937802 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.6998. Min Range: -1.6998

Max Act: 1.1959. Min Act: -0.0003

Data Index: 13503 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 1.6998. Min Range: -1.6998

Max Act: 1.1191. Min Act: -0.0003

Data Index: 415665 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 1.6998. Min Range: -1.6998

Max Act: 1.1011. Min Act: -0.0003

Data Index: 655137 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.6998. Min Range: -1.6998

Max Act: 1.0775. Min Act: -0.0003

Data Index: 301524 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.6998. Min Range: -1.6998

Max Act: 1.0405. Min Act: -0.0003

Data Index: 182968 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 1.6998. Min Range: -1.6998

Max Act: 1.0364. Min Act: -0.0003

Data Index: 1156725 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.6998. Min Range: -1.6998

Max Act: 1.0080. Min Act: -0.0002

Data Index: 694367 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.6998. Min Range: -1.6998

Max Act: 0.9518. Min Act: -0.0003

Data Index: 618795 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 1.6998. Min Range: -1.6998

Max Act: 0.9373. Min Act: -0.0003

Data Index: 85220 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 1.6998. Min Range: -1.6998

Max Act: 0.9609. Min Act: -0.0002

Data Index: 788274 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 1.6998. Min Range: -1.6998

Max Act: 0.9616. Min Act: -0.0003

Data Index: 1007816 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.6998. Min Range: -1.6998

Max Act: 0.9165. Min Act: -0.0003

Data Index: 212628 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.6998. Min Range: -1.6998

Max Act: 0.9457. Min Act: -0.0003

Data Index: 1322874 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.6998. Min Range: -1.6998

Max Act: 0.9314. Min Act: -0.0002

Data Index: 1244392 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.6998. Min Range: -1.6998

Max Act: 0.9463. Min Act: -0.0002

Data Index: 1261840 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 1.6998. Min Range: -1.6998

Max Act: 0.8533. Min Act: -0.0003

Data Index: 438405 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.6998. Min Range: -1.6998

Max Act: 0.8753. Min Act: -0.0003

Data Index: 381238 (C4 (Web Text))

Max Activating Token Index: 852