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

Dataset: The Pile

Neuron 2746 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: 1.5526. Min Range: -1.5526

Max Act: 1.5500. Min Act: -0.0000

Data Index: 846260 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.5526. Min Act: -0.0000

Data Index: 1881949 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.3510. Min Act: -0.0000

Data Index: 191772 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1945658 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1802602 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.4419. Min Act: -0.0001

Data Index: 1477048 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.4934. Min Act: -0.0000

Data Index: 1197611 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1746189 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1817286 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2507. Min Act: -0.0000

Data Index: 1920690 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1724093 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1622. Min Act: -0.0001

Data Index: 913524 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.3052. Min Act: -0.0000

Data Index: 788273 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2305. Min Act: -0.0000

Data Index: 1596833 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1923. Min Act: -0.0000

Data Index: 939627 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1659625 (The Pile)

Max Activating Token Index: 637

Text #16

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1531154 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1353114 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1380034 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1472. Min Act: -0.0000

Data Index: 1843247 (The Pile)

Max Activating Token Index: 917