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

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

Neuron 48 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1618. Min Range: -1.1618

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1072199 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.1618. Min Range: -1.1618

Max Act: 1.1296. Min Act: -0.0000

Data Index: 310806 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 1.1618. Min Range: -1.1618

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1024084 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.8346. Min Act: -0.0000

Data Index: 667357 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.6480. Min Act: -0.0000

Data Index: 55233 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.6335. Min Act: -0.0000

Data Index: 387168 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.6591. Min Act: -0.0000

Data Index: 212773 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.5898. Min Act: -0.0000

Data Index: 448283 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.6839. Min Act: -0.0000

Data Index: 96743 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.6739. Min Act: -0.0000

Data Index: 684953 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.6617. Min Act: -0.0000

Data Index: 565025 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1086258 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.6332. Min Act: -0.0000

Data Index: 918239 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.5977. Min Act: -0.0000

Data Index: 553892 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1126076 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.5050. Min Act: -0.0000

Data Index: 83212 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.5444. Min Act: -0.0000

Data Index: 728053 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1142625 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.5639. Min Act: -0.0000

Data Index: 531095 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 1.1618. Min Range: -1.1618

Max Act: 0.5066. Min Act: -0.0000

Data Index: 802740 (C4 (Web Text))

Max Activating Token Index: 932