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

Dataset: The Pile

Neuron 137 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.7225. Min Act: -0.0000

Data Index: 201892 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.9574. Min Act: -0.0000

Data Index: 16971 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.4930. Min Act: -0.0000

Data Index: 1588952 (The Pile)

Max Activating Token Index: 908

Text #3

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.7030. Min Act: -0.0000

Data Index: 1947052 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.5252. Min Act: -0.0000

Data Index: 1726389 (The Pile)

Max Activating Token Index: 829

Text #5

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.3562. Min Act: -0.0000

Data Index: 787539 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.1275. Min Act: -0.0000

Data Index: 1989942 (The Pile)

Max Activating Token Index: 882

Text #7

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.3692. Min Act: -0.0000

Data Index: 1481798 (The Pile)

Max Activating Token Index: 275

Text #8

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.2088. Min Act: -0.0000

Data Index: 1666626 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.4444. Min Act: -0.0000

Data Index: 499063 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.4274. Min Act: -0.0000

Data Index: 1208369 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.4120. Min Act: -0.0000

Data Index: 4486 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.5078. Min Act: -0.0000

Data Index: 530241 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.4662. Min Act: -0.0000

Data Index: 523053 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 4.7225. Min Range: -4.7225

Max Act: 2.9972. Min Act: -0.0000

Data Index: 87498 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.3917. Min Act: -0.0000

Data Index: 1313991 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.2467. Min Act: -0.0000

Data Index: 1874997 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.2160. Min Act: -0.0000

Data Index: 1250502 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 4.7225. Min Range: -4.7225

Max Act: 2.9200. Min Act: -0.0000

Data Index: 1308409 (The Pile)

Max Activating Token Index: 754

Text #19

Max Range: 4.7225. Min Range: -4.7225

Max Act: 3.3112. Min Act: -0.0000

Data Index: 1047236 (The Pile)

Max Activating Token Index: 300