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

Dataset: The Pile

Neuron 311 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: 0.9947. Min Range: -0.9947

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1499501 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9147. Min Act: -0.0000

Data Index: 116103 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8360. Min Act: -0.0000

Data Index: 132493 (The Pile)

Max Activating Token Index: 243

Text #3

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8823. Min Act: -0.0000

Data Index: 312033 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1564180 (The Pile)

Max Activating Token Index: 898

Text #5

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1919319 (The Pile)

Max Activating Token Index: 740

Text #6

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8342. Min Act: -0.0000

Data Index: 893010 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8149. Min Act: -0.0000

Data Index: 589245 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1369387 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1807997 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1516086 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7556. Min Act: -0.0000

Data Index: 916378 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1921827 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1219011 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7020. Min Act: -0.0000

Data Index: 453189 (The Pile)

Max Activating Token Index: 996

Text #15

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7202. Min Act: -0.0000

Data Index: 653934 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7359. Min Act: -0.0000

Data Index: 278891 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.6762. Min Act: -0.0000

Data Index: 626789 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1841150 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7010. Min Act: -0.0000

Data Index: 213895 (The Pile)

Max Activating Token Index: 574