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

Dataset: The Pile

Neuron 2270 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.8945. Min Act: -0.0000

Data Index: 1542343 (The Pile)

Max Activating Token Index: 701

Text #1

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1696215 (The Pile)

Max Activating Token Index: 920

Text #2

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.2870. Min Act: -0.0000

Data Index: 1027354 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1283. Min Act: -0.0000

Data Index: 1021189 (The Pile)

Max Activating Token Index: 509

Text #4

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0950. Min Act: -0.0000

Data Index: 624620 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1198. Min Act: -0.0000

Data Index: 873457 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1195. Min Act: -0.0000

Data Index: 511057 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1787. Min Act: -0.0000

Data Index: 431487 (The Pile)

Max Activating Token Index: 275

Text #8

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1615122 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1159219 (The Pile)

Max Activating Token Index: 66

Text #10

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1657018 (The Pile)

Max Activating Token Index: 339

Text #11

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1083. Min Act: -0.0000

Data Index: 547097 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0857. Min Act: -0.0000

Data Index: 846974 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0615. Min Act: -0.0000

Data Index: 1355089 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0856. Min Act: -0.0000

Data Index: 477491 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0204. Min Act: -0.0000

Data Index: 71083 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1108709 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 1.8945. Min Range: -1.8945

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1480270 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0709. Min Act: -0.0000

Data Index: 305449 (The Pile)

Max Activating Token Index: 586

Text #19

Max Range: 1.8945. Min Range: -1.8945

Max Act: 0.9979. Min Act: -0.0000

Data Index: 253253 (The Pile)

Max Activating Token Index: 138