Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 512 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.9730. Min Range: -4.9730

Max Act: 4.9730. Min Act: -0.0000

Data Index: 383706 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 4.9730. Min Range: -4.9730

Max Act: 4.5176. Min Act: -0.0000

Data Index: 150164 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 4.9730. Min Range: -4.9730

Max Act: 4.8411. Min Act: -0.0000

Data Index: 271151 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 4.9730. Min Range: -4.9730

Max Act: 4.1232. Min Act: -0.0000

Data Index: 812990 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.8240. Min Act: -0.0000

Data Index: 165202 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 4.9730. Min Range: -4.9730

Max Act: 4.0349. Min Act: -0.0000

Data Index: 441195 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.9367. Min Act: -0.0000

Data Index: 73144 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.6498. Min Act: -0.0000

Data Index: 666019 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.3687. Min Act: -0.0000

Data Index: 75004 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.1866. Min Act: -0.0000

Data Index: 878108 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.4910. Min Act: -0.0000

Data Index: 1066812 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.3933. Min Act: -0.0000

Data Index: 201469 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.1162. Min Act: -0.0000

Data Index: 1123413 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.4086. Min Act: -0.0000

Data Index: 60508 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.0284. Min Act: -0.0000

Data Index: 189001 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.0037. Min Act: -0.0000

Data Index: 104132 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.1473. Min Act: -0.0000

Data Index: 947894 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 4.9730. Min Range: -4.9730

Max Act: 2.9668. Min Act: -0.0000

Data Index: 119966 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 4.9730. Min Range: -4.9730

Max Act: 3.2155. Min Act: -0.0000

Data Index: 317782 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 4.9730. Min Range: -4.9730

Max Act: 2.9556. Min Act: -0.0000

Data Index: 68788 (C4 (Web Text))

Max Activating Token Index: 809