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

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

Neuron 1738 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3919. Min Range: -6.3919

Max Act: 6.3919. Min Act: -0.0000

Data Index: 396712 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 6.3919. Min Range: -6.3919

Max Act: 5.9485. Min Act: -0.0000

Data Index: 601691 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 6.3919. Min Range: -6.3919

Max Act: 5.8077. Min Act: -0.0000

Data Index: 736187 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 6.3919. Min Range: -6.3919

Max Act: 5.7116. Min Act: -0.0000

Data Index: 505379 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 6.3919. Min Range: -6.3919

Max Act: 6.0344. Min Act: -0.0000

Data Index: 8593 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 6.3919. Min Range: -6.3919

Max Act: 5.3103. Min Act: -0.0000

Data Index: 432670 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 6.3919. Min Range: -6.3919

Max Act: 5.1049. Min Act: -0.0000

Data Index: 276701 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 6.3919. Min Range: -6.3919

Max Act: 5.1311. Min Act: -0.0000

Data Index: 567665 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 6.3919. Min Range: -6.3919

Max Act: 5.2617. Min Act: -0.0000

Data Index: 1293292 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 6.3919. Min Range: -6.3919

Max Act: 5.1949. Min Act: -0.0000

Data Index: 863655 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 6.3919. Min Range: -6.3919

Max Act: 5.0843. Min Act: -0.0000

Data Index: 831130 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 6.3919. Min Range: -6.3919

Max Act: 4.8599. Min Act: -0.0000

Data Index: 1045556 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 6.3919. Min Range: -6.3919

Max Act: 4.7387. Min Act: -0.0000

Data Index: 578828 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 6.3919. Min Range: -6.3919

Max Act: 4.1486. Min Act: -0.0000

Data Index: 335719 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 6.3919. Min Range: -6.3919

Max Act: 4.5331. Min Act: -0.0000

Data Index: 1127402 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 6.3919. Min Range: -6.3919

Max Act: 4.5762. Min Act: -0.0000

Data Index: 65568 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 6.3919. Min Range: -6.3919

Max Act: 4.1726. Min Act: -0.0000

Data Index: 485409 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 6.3919. Min Range: -6.3919

Max Act: 4.1142. Min Act: -0.0000

Data Index: 688975 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 6.3919. Min Range: -6.3919

Max Act: 4.0070. Min Act: -0.0000

Data Index: 283496 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 6.3919. Min Range: -6.3919

Max Act: 4.0082. Min Act: -0.0000

Data Index: 176568 (C4 (Web Text))

Max Activating Token Index: 830