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

Dataset: The Pile

Neuron 3825 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1705137 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1120000 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9825. Min Act: 0.0000

Data Index: 630764 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9487. Min Act: 0.0000

Data Index: 231160 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1177118 (The Pile)

Max Activating Token Index: 807

Text #5

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0778. Min Act: 0.0000

Data Index: 470020 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1395253 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1942868 (The Pile)

Max Activating Token Index: 511

Text #8

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1307980 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9464. Min Act: -0.0000

Data Index: 306540 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9556. Min Act: -0.0000

Data Index: 1181076 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9199. Min Act: -0.0000

Data Index: 582283 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9270. Min Act: -0.0000

Data Index: 838680 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1219012 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1478436 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8915. Min Act: -0.0000

Data Index: 1387530 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8544. Min Act: -0.0000

Data Index: 365687 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1290315 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1719315 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1384128 (The Pile)

Max Activating Token Index: 692