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

Dataset: The Pile

Neuron 2875 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: 0.7648. Min Range: -0.7648

Max Act: 0.7648. Min Act: -0.0000

Data Index: 292565 (The Pile)

Max Activating Token Index: 767

Text #1

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1592269 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1241985 (The Pile)

Max Activating Token Index: 918

Text #3

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6254. Min Act: -0.0000

Data Index: 593647 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1173032 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6492. Min Act: -0.0000

Data Index: 40077 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5666. Min Act: -0.0000

Data Index: 761714 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5362. Min Act: -0.0000

Data Index: 516676 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5701. Min Act: -0.0000

Data Index: 895643 (The Pile)

Max Activating Token Index: 432

Text #9

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1242138 (The Pile)

Max Activating Token Index: 428

Text #10

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5278. Min Act: -0.0000

Data Index: 784371 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5059. Min Act: -0.0000

Data Index: 871940 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1728669 (The Pile)

Max Activating Token Index: 680

Text #13

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5272. Min Act: -0.0000

Data Index: 257563 (The Pile)

Max Activating Token Index: 289

Text #14

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1898437 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1291168 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1379293 (The Pile)

Max Activating Token Index: 253

Text #17

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1921749 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5110. Min Act: -0.0000

Data Index: 50924 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4908. Min Act: -0.0000

Data Index: 664982 (The Pile)

Max Activating Token Index: 937