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

Dataset: The Pile

Neuron 1483 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: 1.1604. Min Range: -1.1604

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1125211 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.0925. Min Act: -0.0000

Data Index: 798390 (The Pile)

Max Activating Token Index: 751

Text #2

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1160851 (The Pile)

Max Activating Token Index: 709

Text #3

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1740222 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1562036 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1206760 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1310169 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8996. Min Act: -0.0000

Data Index: 619058 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1304332 (The Pile)

Max Activating Token Index: 675

Text #9

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1943258 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9372. Min Act: -0.0000

Data Index: 958484 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1829523 (The Pile)

Max Activating Token Index: 659

Text #12

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9320. Min Act: -0.0000

Data Index: 938460 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9185. Min Act: -0.0000

Data Index: 766258 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1983294 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8606. Min Act: -0.0000

Data Index: 198215 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8942. Min Act: -0.0000

Data Index: 207842 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1696662 (The Pile)

Max Activating Token Index: 611

Text #18

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8218. Min Act: -0.0000

Data Index: 455633 (The Pile)

Max Activating Token Index: 194

Text #19

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1109055 (The Pile)

Max Activating Token Index: 361