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

Dataset: The Pile

Neuron 3088 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.3421. Min Act: -0.0000

Data Index: 262903 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1527874 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.2827. Min Act: -0.0000

Data Index: 782359 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1170957 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1058. Min Act: -0.0000

Data Index: 414105 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0958. Min Act: -0.0000

Data Index: 980812 (The Pile)

Max Activating Token Index: 351

Text #6

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1318437 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1687357 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9304. Min Act: -0.0000

Data Index: 876123 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1395542 (The Pile)

Max Activating Token Index: 316

Text #10

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0325. Min Act: -0.0000

Data Index: 353062 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1183075 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1798772 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0226. Min Act: -0.0000

Data Index: 635579 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1438665 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1867357 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1014780 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1119714 (The Pile)

Max Activating Token Index: 167

Text #18

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9622. Min Act: -0.0000

Data Index: 572621 (The Pile)

Max Activating Token Index: 514

Text #19

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9657. Min Act: -0.0000

Data Index: 225222 (The Pile)

Max Activating Token Index: 24