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

Dataset: The Pile

Neuron 1259 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: 3.9901. Min Range: -3.9901

Max Act: 3.9901. Min Act: -0.0000

Data Index: 1807031 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.9531. Min Act: -0.0000

Data Index: 1884914 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.8198. Min Act: -0.0000

Data Index: 1745412 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.8187. Min Act: -0.0000

Data Index: 1373402 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.5113. Min Act: -0.0000

Data Index: 1389195 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.6753. Min Act: -0.0000

Data Index: 1716164 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.6386. Min Act: -0.0000

Data Index: 1054141 (The Pile)

Max Activating Token Index: 405

Text #7

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.4902. Min Act: -0.0000

Data Index: 1289728 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.5879. Min Act: -0.0000

Data Index: 1655917 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.7358. Min Act: -0.0000

Data Index: 1148402 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.4026. Min Act: -0.0000

Data Index: 1561940 (The Pile)

Max Activating Token Index: 765

Text #11

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.3981. Min Act: -0.0000

Data Index: 178396 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.3891. Min Act: -0.0000

Data Index: 733032 (The Pile)

Max Activating Token Index: 660

Text #13

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.5405. Min Act: -0.0000

Data Index: 1946342 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.3567. Min Act: -0.0000

Data Index: 122536 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.3453. Min Act: -0.0000

Data Index: 558856 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.5019. Min Act: -0.0000

Data Index: 1381369 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.4650. Min Act: -0.0000

Data Index: 1680072 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.3293. Min Act: -0.0000

Data Index: 861477 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 3.9901. Min Range: -3.9901

Max Act: 3.3061. Min Act: -0.0000

Data Index: 1183436 (The Pile)

Max Activating Token Index: 36