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

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

Neuron 4350 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.8494. Min Act: -0.0000

Data Index: 982305 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5931. Min Act: -0.0000

Data Index: 334539 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1223959 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1213472 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6333. Min Act: -0.0000

Data Index: 777325 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.4982. Min Act: -0.0000

Data Index: 462802 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5996. Min Act: -0.0000

Data Index: 192 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5817. Min Act: -0.0000

Data Index: 330526 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5684. Min Act: -0.0000

Data Index: 552202 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5305. Min Act: -0.0000

Data Index: 26091 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.4803. Min Act: -0.0000

Data Index: 637577 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5463. Min Act: -0.0000

Data Index: 704069 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5447. Min Act: -0.0000

Data Index: 928255 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5008. Min Act: -0.0000

Data Index: 653523 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5114. Min Act: -0.0000

Data Index: 890982 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.4584. Min Act: -0.0000

Data Index: 152524 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.4803. Min Act: -0.0000

Data Index: 6935 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5133. Min Act: -0.0000

Data Index: 937442 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.4982. Min Act: -0.0000

Data Index: 633725 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1291774 (C4 (Web Text))

Max Activating Token Index: 505