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

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

Neuron 1721 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1580. Min Range: -2.1580

Max Act: 2.1580. Min Act: -0.0000

Data Index: 606429 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.8679. Min Act: -0.0000

Data Index: 191537 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.8056. Min Act: -0.0000

Data Index: 970579 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.5633. Min Act: -0.0000

Data Index: 373342 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.7381. Min Act: -0.0000

Data Index: 936388 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.6193. Min Act: -0.0000

Data Index: 181516 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.5961. Min Act: -0.0000

Data Index: 1110235 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.6863. Min Act: -0.0000

Data Index: 66539 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.6004. Min Act: -0.0000

Data Index: 153097 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.5821. Min Act: -0.0000

Data Index: 97692 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.4546. Min Act: -0.0000

Data Index: 1116792 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.5311. Min Act: -0.0000

Data Index: 921089 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.6107. Min Act: -0.0000

Data Index: 56008 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.4155. Min Act: -0.0000

Data Index: 130033 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.4940. Min Act: -0.0000

Data Index: 387825 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.5718. Min Act: -0.0000

Data Index: 292654 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.5717. Min Act: -0.0000

Data Index: 776813 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.4821. Min Act: -0.0000

Data Index: 321146 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1343436 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 2.1580. Min Range: -2.1580

Max Act: 1.2614. Min Act: -0.0000

Data Index: 783189 (C4 (Web Text))

Max Activating Token Index: 151