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

Dataset: The Pile

Neuron 1867 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: 1.4431. Min Range: -1.4431

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1883695 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1946165 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.3420. Min Act: -0.0000

Data Index: 476707 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.2746. Min Act: -0.0000

Data Index: 483594 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1145356 (The Pile)

Max Activating Token Index: 961

Text #5

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.2807. Min Act: -0.0001

Data Index: 1810884 (The Pile)

Max Activating Token Index: 760

Text #6

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.3552. Min Act: -0.0000

Data Index: 1605314 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.2518. Min Act: -0.0000

Data Index: 120344 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.2289. Min Act: -0.0000

Data Index: 559870 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.1733. Min Act: -0.0000

Data Index: 1607546 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.1148. Min Act: -0.0000

Data Index: 654706 (The Pile)

Max Activating Token Index: 867

Text #11

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9188. Min Act: -0.0000

Data Index: 1719048 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0199. Min Act: -0.0000

Data Index: 428280 (The Pile)

Max Activating Token Index: 75

Text #13

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0055. Min Act: -0.0000

Data Index: 342294 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0576. Min Act: -0.0000

Data Index: 247441 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1323616 (The Pile)

Max Activating Token Index: 434

Text #16

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0076. Min Act: -0.0000

Data Index: 843082 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0408. Min Act: -0.0000

Data Index: 808002 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.8771. Min Act: -0.0000

Data Index: 1820218 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1121943 (The Pile)

Max Activating Token Index: 966