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

Dataset: The Pile

Neuron 1173 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: 5.2028. Min Range: -5.2028

Max Act: 5.2028. Min Act: -0.0000

Data Index: 1024427 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 5.2028. Min Range: -5.2028

Max Act: 4.7111. Min Act: -0.0000

Data Index: 941418 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 5.2028. Min Range: -5.2028

Max Act: 4.5368. Min Act: -0.0000

Data Index: 1711386 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 5.2028. Min Range: -5.2028

Max Act: 4.0724. Min Act: -0.0000

Data Index: 108698 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 5.2028. Min Range: -5.2028

Max Act: 4.3735. Min Act: -0.0000

Data Index: 131155 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 5.2028. Min Range: -5.2028

Max Act: 4.1773. Min Act: -0.0000

Data Index: 1067697 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 5.2028. Min Range: -5.2028

Max Act: 4.3404. Min Act: -0.0000

Data Index: 1385751 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 5.2028. Min Range: -5.2028

Max Act: 4.0191. Min Act: -0.0000

Data Index: 628325 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.9828. Min Act: -0.0000

Data Index: 232319 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.6010. Min Act: -0.0000

Data Index: 1206323 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.7908. Min Act: -0.0000

Data Index: 1083780 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.9282. Min Act: -0.0000

Data Index: 1546041 (The Pile)

Max Activating Token Index: 242

Text #12

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.5923. Min Act: -0.0000

Data Index: 36397 (The Pile)

Max Activating Token Index: 700

Text #13

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.8902. Min Act: -0.0000

Data Index: 325301 (The Pile)

Max Activating Token Index: 513

Text #14

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.7520. Min Act: -0.0000

Data Index: 1557404 (The Pile)

Max Activating Token Index: 299

Text #15

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.8427. Min Act: -0.0000

Data Index: 1418217 (The Pile)

Max Activating Token Index: 209

Text #16

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.6046. Min Act: -0.0000

Data Index: 1977145 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.8542. Min Act: -0.0000

Data Index: 720976 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 5.2028. Min Range: -5.2028

Max Act: 3.7228. Min Act: -0.0000

Data Index: 1703988 (The Pile)

Max Activating Token Index: 294

Text #19

Max Range: 5.2028. Min Range: -5.2028

Max Act: 4.0408. Min Act: -0.0000

Data Index: 1585885 (The Pile)

Max Activating Token Index: 233