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

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

Neuron 4444 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1334. Min Act: -0.0002

Data Index: 669133 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1071. Min Act: -0.0002

Data Index: 198808 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1120816 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0983. Min Act: -0.0002

Data Index: 51999 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0898. Min Act: -0.0002

Data Index: 925910 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0787. Min Act: -0.0002

Data Index: 814301 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0856. Min Act: -0.0002

Data Index: 416453 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0834. Min Act: -0.0002

Data Index: 832652 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0798. Min Act: -0.0002

Data Index: 230869 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1074461 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0771. Min Act: -0.0002

Data Index: 994471 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1181346 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0818. Min Act: -0.0002

Data Index: 351468 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0808. Min Act: -0.0002

Data Index: 483161 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0729. Min Act: -0.0002

Data Index: 167471 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0788. Min Act: -0.0002

Data Index: 33626 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0727. Min Act: -0.0002

Data Index: 685781 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0788. Min Act: -0.0002

Data Index: 223298 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0736. Min Act: -0.0002

Data Index: 295660 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1282933 (C4 (Web Text))

Max Activating Token Index: 310