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

Dataset: The Pile

Neuron 1593 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.4161. Min Act: -0.0000

Data Index: 1079439 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.3208. Min Act: -0.0000

Data Index: 507369 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.2829. Min Act: -0.0000

Data Index: 720871 (The Pile)

Max Activating Token Index: 257

Text #3

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.2034. Min Act: -0.0000

Data Index: 1893328 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.1877. Min Act: -0.0000

Data Index: 1647411 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.4201. Min Act: -0.0000

Data Index: 230616 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.2257. Min Act: -0.0000

Data Index: 809986 (The Pile)

Max Activating Token Index: 910

Text #7

Max Range: 3.4722. Min Range: -3.4722

Max Act: 2.8842. Min Act: -0.0000

Data Index: 35857 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.4722. Min Act: -0.0000

Data Index: 1095815 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 3.4722. Min Range: -3.4722

Max Act: 2.8633. Min Act: -0.0000

Data Index: 396580 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.2957. Min Act: -0.0000

Data Index: 1204878 (The Pile)

Max Activating Token Index: 904

Text #11

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.0442. Min Act: -0.0000

Data Index: 1519024 (The Pile)

Max Activating Token Index: 77

Text #12

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.0213. Min Act: -0.0000

Data Index: 1316049 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.0571. Min Act: -0.0000

Data Index: 1861946 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.0099. Min Act: -0.0000

Data Index: 678997 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 3.4722. Min Range: -3.4722

Max Act: 2.9216. Min Act: -0.0000

Data Index: 428804 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 3.4722. Min Range: -3.4722

Max Act: 2.8949. Min Act: -0.0000

Data Index: 149206 (The Pile)

Max Activating Token Index: 786

Text #17

Max Range: 3.4722. Min Range: -3.4722

Max Act: 2.9726. Min Act: -0.0000

Data Index: 221962 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 3.4722. Min Range: -3.4722

Max Act: 3.1005. Min Act: -0.0000

Data Index: 458547 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 3.4722. Min Range: -3.4722

Max Act: 2.7188. Min Act: -0.0000

Data Index: 338069 (The Pile)

Max Activating Token Index: 42