Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3798 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.8690. Min Act: -0.0000

Data Index: 487939 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1627151 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1939917 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 1.0137. Min Range: -1.0137

Max Act: 1.0137. Min Act: -0.0000

Data Index: 394478 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1999720 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.8902. Min Act: -0.0000

Data Index: 1642843 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.8213. Min Act: -0.0000

Data Index: 385237 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.8203. Min Act: -0.0000

Data Index: 447802 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1594427 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1444649 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1350703 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1587167 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7890. Min Act: -0.0000

Data Index: 755127 (The Pile)

Max Activating Token Index: 168

Text #13

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1796038 (The Pile)

Max Activating Token Index: 658

Text #14

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7335. Min Act: -0.0000

Data Index: 429599 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1649992 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1178974 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.8206. Min Act: -0.0000

Data Index: 293701 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7613. Min Act: -0.0000

Data Index: 726622 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1382812 (The Pile)

Max Activating Token Index: 762