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

Dataset: The Pile

Neuron 472 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.6210. Min Act: -0.0000

Data Index: 1111643 (The Pile)

Max Activating Token Index: 787

Text #1

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1918779 (The Pile)

Max Activating Token Index: 244

Text #2

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1069835 (The Pile)

Max Activating Token Index: 222

Text #3

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.2022. Min Act: -0.0000

Data Index: 670378 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1609272 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.1633. Min Act: -0.0000

Data Index: 263854 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.1909. Min Act: -0.0000

Data Index: 601174 (The Pile)

Max Activating Token Index: 280

Text #7

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.0937. Min Act: -0.0000

Data Index: 608414 (The Pile)

Max Activating Token Index: 725

Text #8

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.1005. Min Act: -0.0000

Data Index: 192284 (The Pile)

Max Activating Token Index: 403

Text #9

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1202335 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1148449 (The Pile)

Max Activating Token Index: 601

Text #11

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1883465 (The Pile)

Max Activating Token Index: 322

Text #12

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1274158 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1486354 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 1.6210. Min Range: -1.6210

Max Act: 0.9917. Min Act: -0.0000

Data Index: 538843 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.0510. Min Act: -0.0000

Data Index: 925970 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1140482 (The Pile)

Max Activating Token Index: 250

Text #17

Max Range: 1.6210. Min Range: -1.6210

Max Act: 0.9651. Min Act: -0.0000

Data Index: 783720 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.0332. Min Act: -0.0000

Data Index: 195659 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 1.6210. Min Range: -1.6210

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1417088 (The Pile)

Max Activating Token Index: 822