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

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

Neuron 4509 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5907. Min Act: -0.0000

Data Index: 600323 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1348995 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5265. Min Act: -0.0000

Data Index: 365862 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4786. Min Act: -0.0000

Data Index: 436672 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4661. Min Act: -0.0000

Data Index: 485074 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1174098 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1098588 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4551. Min Act: 0.0000

Data Index: 703897 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1059970 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4524. Min Act: -0.0000

Data Index: 425655 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4506. Min Act: -0.0000

Data Index: 426197 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4777. Min Act: -0.0000

Data Index: 56152 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4562. Min Act: -0.0000

Data Index: 120336 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4556. Min Act: -0.0000

Data Index: 906474 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4574. Min Act: 0.0000

Data Index: 396897 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4567. Min Act: -0.0000

Data Index: 375647 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4283. Min Act: -0.0000

Data Index: 536566 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4522. Min Act: 0.0000

Data Index: 345305 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1004974 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4575. Min Act: -0.0000

Data Index: 500508 (C4 (Web Text))

Max Activating Token Index: 24