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

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

Neuron 3347 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2347. Min Range: -2.2347

Max Act: 2.0337. Min Act: -0.0000

Data Index: 947929 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 2.2347. Min Range: -2.2347

Max Act: 2.0019. Min Act: -0.0000

Data Index: 1092645 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.7765. Min Act: -0.0000

Data Index: 411587 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 2.2347. Min Range: -2.2347

Max Act: 2.2347. Min Act: -0.0000

Data Index: 670188 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.9119. Min Act: -0.0000

Data Index: 896134 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.8504. Min Act: -0.0001

Data Index: 1225727 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.5395. Min Act: -0.0000

Data Index: 701059 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.8101. Min Act: -0.0000

Data Index: 156899 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.6723. Min Act: -0.0000

Data Index: 567155 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.7325. Min Act: -0.0000

Data Index: 1013971 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.7504. Min Act: -0.0000

Data Index: 26956 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.7543. Min Act: -0.0000

Data Index: 110272 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.5572. Min Act: -0.0000

Data Index: 251505 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.3710. Min Act: -0.0000

Data Index: 778436 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.6840. Min Act: -0.0000

Data Index: 90973 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.5713. Min Act: -0.0000

Data Index: 821331 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1079926 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.6713. Min Act: -0.0000

Data Index: 632775 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.4828. Min Act: -0.0000

Data Index: 324381 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 2.2347. Min Range: -2.2347

Max Act: 1.6557. Min Act: -0.0000

Data Index: 299872 (C4 (Web Text))

Max Activating Token Index: 434