Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.8533. Min Act: -0.0002

Data Index: 720271 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.7141. Min Act: -0.0001

Data Index: 25708 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.7792. Min Act: -0.0001

Data Index: 450843 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.7620. Min Act: -0.0002

Data Index: 126255 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.6316. Min Act: -0.0002

Data Index: 707226 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.7389. Min Act: -0.0001

Data Index: 460422 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.5489. Min Act: -0.0001

Data Index: 861538 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.6233. Min Act: -0.0002

Data Index: 1183104 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.5850. Min Act: -0.0001

Data Index: 572035 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.5599. Min Act: -0.0001

Data Index: 188609 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.5660. Min Act: -0.0002

Data Index: 165760 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.5531. Min Act: -0.0001

Data Index: 1260006 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.5299. Min Act: -0.0001

Data Index: 695406 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.5241. Min Act: -0.0001

Data Index: 922110 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.5992. Min Act: -0.0001

Data Index: 306805 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.4833. Min Act: -0.0002

Data Index: 3711 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.4962. Min Act: -0.0002

Data Index: 716536 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.4912. Min Act: -0.0001

Data Index: 1204727 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.5250. Min Act: -0.0002

Data Index: 775138 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.8533. Min Range: -1.8533

Max Act: 1.4291. Min Act: -0.0001

Data Index: 415230 (C4 (Web Text))

Max Activating Token Index: 795