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

Dataset: The Pile

Neuron 2152 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.4693. Min Act: -0.0000

Data Index: 763540 (The Pile)

Max Activating Token Index: 820

Text #1

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1836. Min Act: -0.0000

Data Index: 9500 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.4011. Min Act: -0.0000

Data Index: 1728406 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1146335 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.3020. Min Act: -0.0000

Data Index: 893247 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1853. Min Act: -0.0000

Data Index: 1263657 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1950247 (The Pile)

Max Activating Token Index: 956

Text #7

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1159461 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1401. Min Act: -0.0000

Data Index: 445693 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1070716 (The Pile)

Max Activating Token Index: 607

Text #10

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.0917. Min Act: -0.0000

Data Index: 886685 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 1.4693. Min Range: -1.4693

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1904809 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1231. Min Act: -0.0000

Data Index: 345779 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1667296 (The Pile)

Max Activating Token Index: 929

Text #14

Max Range: 1.4693. Min Range: -1.4693

Max Act: 1.2132. Min Act: -0.0000

Data Index: 260953 (The Pile)

Max Activating Token Index: 928

Text #15

Max Range: 1.4693. Min Range: -1.4693

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1123608 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.4693. Min Range: -1.4693

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1278207 (The Pile)

Max Activating Token Index: 165

Text #17

Max Range: 1.4693. Min Range: -1.4693

Max Act: 0.9383. Min Act: -0.0000

Data Index: 883227 (The Pile)

Max Activating Token Index: 822

Text #18

Max Range: 1.4693. Min Range: -1.4693

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1937601 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 1.4693. Min Range: -1.4693

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1439049 (The Pile)

Max Activating Token Index: 225