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

Dataset: The Pile

Neuron 5103 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7763. Min Act: -0.0000

Data Index: 1852308 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.9626. Min Act: -0.0000

Data Index: 1403977 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6625. Min Act: -0.0000

Data Index: 136477 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.5800. Min Act: -0.0000

Data Index: 242360 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6485. Min Act: -0.0000

Data Index: 1991041 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.3194. Min Act: -0.0000

Data Index: 727439 (The Pile)

Max Activating Token Index: 201

Text #6

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6075. Min Act: -0.0000

Data Index: 1435598 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.2383. Min Act: -0.0000

Data Index: 818092 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.0981. Min Act: -0.0000

Data Index: 1260891 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.2002. Min Act: -0.0000

Data Index: 271371 (The Pile)

Max Activating Token Index: 716

Text #10

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.5203. Min Act: -0.0000

Data Index: 141851 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.3593. Min Act: -0.0000

Data Index: 326790 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.3133. Min Act: -0.0000

Data Index: 1577937 (The Pile)

Max Activating Token Index: 170

Text #13

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.1221. Min Act: -0.0000

Data Index: 1493303 (The Pile)

Max Activating Token Index: 4

Text #14

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.4370. Min Act: -0.0000

Data Index: 1280012 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.0927. Min Act: -0.0000

Data Index: 1679945 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.2545. Min Act: -0.0000

Data Index: 792793 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.2254. Min Act: -0.0000

Data Index: 444558 (The Pile)

Max Activating Token Index: 934

Text #18

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.0798. Min Act: -0.0000

Data Index: 1428974 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.1939. Min Act: -0.0000

Data Index: 1129536 (The Pile)

Max Activating Token Index: 762