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

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

Neuron 905 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.9793. Min Act: -0.0000

Data Index: 1315844 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.9119. Min Act: -0.0000

Data Index: 698358 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.4995. Min Act: -0.0000

Data Index: 1266537 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.6209. Min Act: -0.0000

Data Index: 605628 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.3397. Min Act: -0.0000

Data Index: 299993 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.5675. Min Act: -0.0000

Data Index: 793397 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.4537. Min Act: -0.0000

Data Index: 1194041 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.4070. Min Act: -0.0000

Data Index: 290475 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.2800. Min Act: -0.0000

Data Index: 918342 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.3688. Min Act: -0.0000

Data Index: 197920 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.3987. Min Act: -0.0000

Data Index: 458887 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.2518. Min Act: -0.0000

Data Index: 133458 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.3122. Min Act: -0.0000

Data Index: 87058 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.0061. Min Act: -0.0000

Data Index: 43603 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.9793. Min Range: -2.9793

Max Act: 1.9623. Min Act: -0.0000

Data Index: 182437 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 2.9793. Min Range: -2.9793

Max Act: 2.1181. Min Act: -0.0000

Data Index: 1180288 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 2.9793. Min Range: -2.9793

Max Act: 1.8783. Min Act: -0.0000

Data Index: 160698 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 2.9793. Min Range: -2.9793

Max Act: 1.8564. Min Act: -0.0000

Data Index: 95859 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 2.9793. Min Range: -2.9793

Max Act: 1.7617. Min Act: -0.0000

Data Index: 498973 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 2.9793. Min Range: -2.9793

Max Act: 1.7353. Min Act: -0.0000

Data Index: 788527 (C4 (Web Text))

Max Activating Token Index: 75