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

Dataset: The Pile

Neuron 4697 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.1529. Min Range: -5.1529

Max Act: 5.1529. Min Act: -0.0000

Data Index: 1505955 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.9646. Min Act: -0.0000

Data Index: 635849 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.9721. Min Act: -0.0000

Data Index: 1995621 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.9632. Min Act: -0.0000

Data Index: 458399 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.9246. Min Act: -0.0000

Data Index: 1810442 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.8565. Min Act: -0.0000

Data Index: 547111 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.8141. Min Act: -0.0000

Data Index: 519826 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.5088. Min Act: -0.0000

Data Index: 1419108 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.5787. Min Act: -0.0000

Data Index: 147137 (The Pile)

Max Activating Token Index: 768

Text #9

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.5828. Min Act: -0.0000

Data Index: 1950127 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.7387. Min Act: -0.0000

Data Index: 849103 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.7112. Min Act: -0.0000

Data Index: 34203 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.7211. Min Act: -0.0000

Data Index: 1776408 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.4639. Min Act: -0.0000

Data Index: 962017 (The Pile)

Max Activating Token Index: 984

Text #14

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.6130. Min Act: -0.0000

Data Index: 27573 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.3977. Min Act: -0.0000

Data Index: 988677 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.5779. Min Act: -0.0000

Data Index: 377326 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.7298. Min Act: -0.0000

Data Index: 1478452 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.5205. Min Act: -0.0000

Data Index: 872908 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 5.1529. Min Range: -5.1529

Max Act: 4.7166. Min Act: -0.0000

Data Index: 1715683 (The Pile)

Max Activating Token Index: 630