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

Dataset: The Pile

Neuron 3261 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: 1.2888. Min Range: -1.2888

Max Act: 1.2888. Min Act: -0.0000

Data Index: 473636 (The Pile)

Max Activating Token Index: 287

Text #1

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1556436 (The Pile)

Max Activating Token Index: 298

Text #2

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.2140. Min Act: -0.0000

Data Index: 947159 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1642169 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.1905. Min Act: -0.0000

Data Index: 898184 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.1312. Min Act: -0.0000

Data Index: 672469 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.2143. Min Act: -0.0000

Data Index: 903463 (The Pile)

Max Activating Token Index: 387

Text #7

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.2126. Min Act: -0.0000

Data Index: 256014 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.0704. Min Act: -0.0000

Data Index: 958751 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1604160 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.1864. Min Act: -0.0000

Data Index: 1420087 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1231702 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.1715. Min Act: -0.0000

Data Index: 115376 (The Pile)

Max Activating Token Index: 680

Text #13

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1362228 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1188064 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1110352 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.0431. Min Act: -0.0000

Data Index: 483779 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.0686. Min Act: -0.0000

Data Index: 114920 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.0338. Min Act: -0.0000

Data Index: 146651 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 1.2888. Min Range: -1.2888

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1079069 (The Pile)

Max Activating Token Index: 319