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

Dataset: The Pile

Neuron 3598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.5263. Min Act: -0.0000

Data Index: 682966 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1611198 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4079. Min Act: -0.0000

Data Index: 31673 (The Pile)

Max Activating Token Index: 874

Text #3

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4006. Min Act: -0.0000

Data Index: 622457 (The Pile)

Max Activating Token Index: 684

Text #4

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1025937 (The Pile)

Max Activating Token Index: 974

Text #5

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4043. Min Act: -0.0000

Data Index: 597588 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1903338 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1163330 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4087. Min Act: -0.0000

Data Index: 459038 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1927777 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4198. Min Act: -0.0000

Data Index: 310576 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1912870 (The Pile)

Max Activating Token Index: 909

Text #12

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4052. Min Act: -0.0000

Data Index: 899671 (The Pile)

Max Activating Token Index: 385

Text #13

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4065. Min Act: -0.0000

Data Index: 749006 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3815. Min Act: -0.0000

Data Index: 515577 (The Pile)

Max Activating Token Index: 850

Text #15

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1719328 (The Pile)

Max Activating Token Index: 210

Text #16

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1037613 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4107. Min Act: -0.0000

Data Index: 540369 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1393871 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1678220 (The Pile)

Max Activating Token Index: 627