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

Dataset: The Pile

Neuron 230 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: 1.5374. Min Range: -1.5374

Max Act: 1.5374. Min Act: -0.0000

Data Index: 1351849 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1364842 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.4821. Min Act: -0.0000

Data Index: 1656470 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.4321. Min Act: -0.0000

Data Index: 909447 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1756380 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.2449. Min Act: -0.0000

Data Index: 1365451 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.3981. Min Act: -0.0000

Data Index: 1967067 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1954267 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1616911 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1272713 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.4392. Min Act: -0.0000

Data Index: 1979700 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.3801. Min Act: -0.0000

Data Index: 422889 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.2860. Min Act: -0.0000

Data Index: 1318538 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.2141. Min Act: -0.0000

Data Index: 633296 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.3714. Min Act: -0.0000

Data Index: 809307 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1894659 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1473476 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.1890. Min Act: -0.0000

Data Index: 918558 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1214203 (The Pile)

Max Activating Token Index: 734

Text #19

Max Range: 1.5374. Min Range: -1.5374

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1640505 (The Pile)

Max Activating Token Index: 579