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

Dataset: The Pile

Neuron 4619 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: 0.7600. Min Range: -0.7600

Max Act: 0.7600. Min Act: -0.0000

Data Index: 723928 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5420. Min Act: -0.0000

Data Index: 968385 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5566. Min Act: -0.0000

Data Index: 379673 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1506066 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4921. Min Act: -0.0000

Data Index: 93494 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5011. Min Act: -0.0000

Data Index: 109981 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5159. Min Act: -0.0000

Data Index: 503755 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4833. Min Act: -0.0000

Data Index: 585305 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5147. Min Act: -0.0000

Data Index: 440865 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4990. Min Act: -0.0000

Data Index: 895315 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1253397 (The Pile)

Max Activating Token Index: 540

Text #11

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5177. Min Act: -0.0000

Data Index: 686245 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4814. Min Act: -0.0000

Data Index: 624810 (The Pile)

Max Activating Token Index: 128

Text #13

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4202. Min Act: -0.0000

Data Index: 672499 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5122. Min Act: -0.0000

Data Index: 64023 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4940. Min Act: -0.0000

Data Index: 588902 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4760. Min Act: -0.0000

Data Index: 738104 (The Pile)

Max Activating Token Index: 752

Text #17

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1296893 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4552. Min Act: -0.0000

Data Index: 36606 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4687. Min Act: -0.0000

Data Index: 359089 (The Pile)

Max Activating Token Index: 461