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

Dataset: The Pile

Neuron 1288 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4291. Min Range: -5.4291

Max Act: 5.3873. Min Act: -0.0000

Data Index: 1030980 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 5.4291. Min Range: -5.4291

Max Act: 5.4291. Min Act: -0.0000

Data Index: 1002889 (The Pile)

Max Activating Token Index: 6

Text #2

Max Range: 5.4291. Min Range: -5.4291

Max Act: 4.5898. Min Act: -0.0000

Data Index: 577569 (The Pile)

Max Activating Token Index: 707

Text #3

Max Range: 5.4291. Min Range: -5.4291

Max Act: 4.3100. Min Act: -0.0000

Data Index: 1732703 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 5.4291. Min Range: -5.4291

Max Act: 4.2652. Min Act: -0.0000

Data Index: 491861 (The Pile)

Max Activating Token Index: 6

Text #5

Max Range: 5.4291. Min Range: -5.4291

Max Act: 4.5327. Min Act: -0.0000

Data Index: 1293622 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 5.4291. Min Range: -5.4291

Max Act: 4.7833. Min Act: -0.0000

Data Index: 1539964 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 5.4291. Min Range: -5.4291

Max Act: 3.8941. Min Act: -0.0000

Data Index: 803909 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 5.4291. Min Range: -5.4291

Max Act: 4.1945. Min Act: -0.0000

Data Index: 1364085 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 5.4291. Min Range: -5.4291

Max Act: 4.3558. Min Act: -0.0000

Data Index: 107593 (The Pile)

Max Activating Token Index: 6

Text #10

Max Range: 5.4291. Min Range: -5.4291

Max Act: 3.8362. Min Act: -0.0000

Data Index: 892458 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 5.4291. Min Range: -5.4291

Max Act: 4.1622. Min Act: -0.0000

Data Index: 1594997 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 5.4291. Min Range: -5.4291

Max Act: 4.0591. Min Act: -0.0000

Data Index: 345668 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 5.4291. Min Range: -5.4291

Max Act: 3.8441. Min Act: -0.0000

Data Index: 914067 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 5.4291. Min Range: -5.4291

Max Act: 3.8489. Min Act: -0.0000

Data Index: 1766157 (The Pile)

Max Activating Token Index: 925

Text #15

Max Range: 5.4291. Min Range: -5.4291

Max Act: 3.9200. Min Act: -0.0000

Data Index: 1043217 (The Pile)

Max Activating Token Index: 980

Text #16

Max Range: 5.4291. Min Range: -5.4291

Max Act: 3.9014. Min Act: -0.0000

Data Index: 174390 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 5.4291. Min Range: -5.4291

Max Act: 3.7548. Min Act: -0.0000

Data Index: 1142407 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 5.4291. Min Range: -5.4291

Max Act: 3.9534. Min Act: -0.0000

Data Index: 1815900 (The Pile)

Max Activating Token Index: 401

Text #19

Max Range: 5.4291. Min Range: -5.4291

Max Act: 4.0696. Min Act: -0.0000

Data Index: 906152 (The Pile)

Max Activating Token Index: 382