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

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

Neuron 1829 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3093. Min Range: -3.3093

Max Act: 3.3093. Min Act: -0.0000

Data Index: 825059 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 3.3093. Min Range: -3.3093

Max Act: 2.0207. Min Act: 0.0000

Data Index: 1043521 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.9408. Min Act: -0.0000

Data Index: 781498 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.8948. Min Act: -0.0000

Data Index: 33002 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.8191. Min Act: -0.0000

Data Index: 804539 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.7606. Min Act: -0.0000

Data Index: 57794 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.6185. Min Act: -0.0000

Data Index: 320643 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.5440. Min Act: 0.0000

Data Index: 1085404 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.6926. Min Act: -0.0000

Data Index: 405234 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.6526. Min Act: -0.0000

Data Index: 818047 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.4963. Min Act: -0.0000

Data Index: 194602 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.4165. Min Act: -0.0000

Data Index: 63567 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.4906. Min Act: -0.0000

Data Index: 236958 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.4927. Min Act: -0.0000

Data Index: 654959 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.5096. Min Act: -0.0000

Data Index: 488808 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.4814. Min Act: 0.0000

Data Index: 574346 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.4802. Min Act: -0.0000

Data Index: 837891 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.4299. Min Act: -0.0000

Data Index: 516706 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.4493. Min Act: -0.0000

Data Index: 1145087 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 3.3093. Min Range: -3.3093

Max Act: 1.4531. Min Act: -0.0000

Data Index: 80309 (C4 (Web Text))

Max Activating Token Index: 588