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

Dataset: The Pile

Neuron 307 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0021. Min Range: -1.0021

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1084355 (The Pile)

Max Activating Token Index: 363

Text #1

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1464109 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8851. Min Act: -0.0000

Data Index: 82840 (The Pile)

Max Activating Token Index: 941

Text #3

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1004267 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8985. Min Act: -0.0000

Data Index: 79995 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1439346 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8697. Min Act: -0.0000

Data Index: 522723 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1198412 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1928413 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1724762 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1923616 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7798. Min Act: -0.0000

Data Index: 678466 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7932. Min Act: -0.0000

Data Index: 647477 (The Pile)

Max Activating Token Index: 690

Text #13

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1166017 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1940066 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7825. Min Act: -0.0000

Data Index: 610868 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1952146 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7541. Min Act: -0.0000

Data Index: 532179 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7536. Min Act: -0.0000

Data Index: 41492 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1052943 (The Pile)

Max Activating Token Index: 599