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

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

Neuron 4876 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: 2.3127. Min Range: -2.3127

Max Act: 2.3127. Min Act: -0.0000

Data Index: 1328752 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 2.3127. Min Range: -2.3127

Max Act: 2.2023. Min Act: -0.0000

Data Index: 26111 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.9697. Min Act: -0.0000

Data Index: 385522 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.9461. Min Act: -0.0000

Data Index: 1183820 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 2.3127. Min Range: -2.3127

Max Act: 2.0164. Min Act: -0.0000

Data Index: 896487 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.8238. Min Act: -0.0000

Data Index: 324779 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.8610. Min Act: -0.0000

Data Index: 185187 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.8030. Min Act: -0.0000

Data Index: 1234373 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.7993. Min Act: -0.0000

Data Index: 223651 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.7741. Min Act: -0.0000

Data Index: 164042 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.6107. Min Act: -0.0000

Data Index: 1242091 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.6092. Min Act: -0.0001

Data Index: 1482573 (Python Code)

Max Activating Token Index: 873

Text #12

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.6254. Min Act: -0.0000

Data Index: 919342 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1231998 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.6538. Min Act: -0.0001

Data Index: 1564203 (Python Code)

Max Activating Token Index: 921

Text #15

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.6366. Min Act: -0.0000

Data Index: 882799 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.6061. Min Act: -0.0000

Data Index: 143564 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.5979. Min Act: -0.0000

Data Index: 295592 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.5843. Min Act: -0.0000

Data Index: 1224825 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 2.3127. Min Range: -2.3127

Max Act: 1.5732. Min Act: -0.0000

Data Index: 1436199 (Python Code)

Max Activating Token Index: 480