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

Dataset: The Pile

Neuron 3221 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.7644. Min Act: -0.0000

Data Index: 534224 (The Pile)

Max Activating Token Index: 562

Text #1

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1864765 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6651. Min Act: 0.0001

Data Index: 566242 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1805168 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1685927 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1496828 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6336. Min Act: -0.0000

Data Index: 365298 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1145070 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1939512 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1279243 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5890. Min Act: -0.0000

Data Index: 420618 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1278970 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6129. Min Act: -0.0000

Data Index: 207626 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1010431 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1515218 (The Pile)

Max Activating Token Index: 211

Text #15

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1109129 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6178. Min Act: -0.0000

Data Index: 841160 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1160796 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5570. Min Act: -0.0000

Data Index: 527865 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5743. Min Act: -0.0000

Data Index: 669601 (The Pile)

Max Activating Token Index: 271