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

Dataset: The Pile

Neuron 3829 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1435928 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.9140. Min Act: -0.0000

Data Index: 391805 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.9685. Min Act: -0.0000

Data Index: 1029875 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.8374. Min Act: -0.0000

Data Index: 760272 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.9075. Min Act: -0.0000

Data Index: 950719 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.8539. Min Act: -0.0000

Data Index: 667411 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1297883 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7707. Min Act: -0.0000

Data Index: 530851 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1007491 (The Pile)

Max Activating Token Index: 948

Text #9

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1158495 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1006180 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1073556 (The Pile)

Max Activating Token Index: 468

Text #12

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7344. Min Act: -0.0000

Data Index: 336865 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1710683 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1908684 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1673868 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1618173 (The Pile)

Max Activating Token Index: 707

Text #17

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7151. Min Act: -0.0000

Data Index: 140653 (The Pile)

Max Activating Token Index: 372

Text #18

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.7593. Min Act: -0.0000

Data Index: 278355 (The Pile)

Max Activating Token Index: 47

Text #19

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1663743 (The Pile)

Max Activating Token Index: 357