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

Dataset: The Pile

Neuron 2193 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: 0.8504. Min Range: -0.8504

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1818026 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1198313 (The Pile)

Max Activating Token Index: 139

Text #2

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7683. Min Act: -0.0000

Data Index: 369863 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7588. Min Act: -0.0000

Data Index: 425637 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6891. Min Act: -0.0000

Data Index: 151530 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1256179 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6830. Min Act: -0.0000

Data Index: 800988 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1601725 (The Pile)

Max Activating Token Index: 168

Text #8

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1876072 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1081691 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7523. Min Act: -0.0000

Data Index: 499171 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6791. Min Act: -0.0000

Data Index: 377302 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6166. Min Act: -0.0000

Data Index: 381869 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6488. Min Act: -0.0000

Data Index: 232228 (The Pile)

Max Activating Token Index: 348

Text #14

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6434. Min Act: -0.0000

Data Index: 464358 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6163. Min Act: -0.0000

Data Index: 281719 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6467. Min Act: -0.0000

Data Index: 925449 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1347620 (The Pile)

Max Activating Token Index: 879

Text #18

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1738973 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6332. Min Act: -0.0000

Data Index: 438085 (The Pile)

Max Activating Token Index: 615