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

Dataset: The Pile

Neuron 4668 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: 1.1584. Min Range: -1.1584

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1007692 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 1.1584. Min Range: -1.1584

Max Act: 1.0691. Min Act: -0.0000

Data Index: 218584 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8201. Min Act: -0.0000

Data Index: 1960308 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8417. Min Act: -0.0000

Data Index: 49499 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.9271. Min Act: -0.0000

Data Index: 998988 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1399686 (The Pile)

Max Activating Token Index: 305

Text #6

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.7718. Min Act: -0.0000

Data Index: 169248 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1749584 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.7875. Min Act: -0.0000

Data Index: 136127 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1639267 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1146259 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1865539 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.7150. Min Act: -0.0000

Data Index: 2022 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1834690 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.7164. Min Act: -0.0000

Data Index: 933989 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1148699 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.7687. Min Act: -0.0000

Data Index: 448801 (The Pile)

Max Activating Token Index: 361

Text #17

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.6878. Min Act: -0.0000

Data Index: 649799 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.6735. Min Act: -0.0000

Data Index: 296711 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.6532. Min Act: -0.0000

Data Index: 253816 (The Pile)

Max Activating Token Index: 594