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

Dataset: The Pile

Neuron 1762 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: 1.3894. Min Range: -1.3894

Max Act: 1.3894. Min Act: -0.0000

Data Index: 227646 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.2754. Min Act: -0.0000

Data Index: 292166 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.3875. Min Act: -0.0000

Data Index: 1612778 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.2071. Min Act: -0.0000

Data Index: 246215 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1360. Min Act: -0.0000

Data Index: 675748 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1260. Min Act: 0.0000

Data Index: 1025205 (The Pile)

Max Activating Token Index: 808

Text #6

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0511. Min Act: -0.0000

Data Index: 480093 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1031. Min Act: -0.0000

Data Index: 320064 (The Pile)

Max Activating Token Index: 917

Text #8

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1049. Min Act: -0.0000

Data Index: 294110 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1177105 (The Pile)

Max Activating Token Index: 917

Text #10

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1251881 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0158. Min Act: -0.0000

Data Index: 572469 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 1.3894. Min Range: -1.3894

Max Act: 0.9862. Min Act: -0.0000

Data Index: 312062 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0424. Min Act: -0.0000

Data Index: 1250223 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 1.3894. Min Range: -1.3894

Max Act: 0.9892. Min Act: -0.0000

Data Index: 714080 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0946. Min Act: -0.0000

Data Index: 530187 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0431. Min Act: -0.0000

Data Index: 612980 (The Pile)

Max Activating Token Index: 942

Text #17

Max Range: 1.3894. Min Range: -1.3894

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1527521 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 1.3894. Min Range: -1.3894

Max Act: 0.9781. Min Act: -0.0000

Data Index: 333274 (The Pile)

Max Activating Token Index: 966

Text #19

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1015. Min Act: -0.0000

Data Index: 790531 (The Pile)

Max Activating Token Index: 796