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

Dataset: The Pile

Neuron 2166 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.7638. Min Act: -0.0000

Data Index: 18643 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.0279. Min Act: -0.0000

Data Index: 767793 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.4186. Min Act: -0.0000

Data Index: 1127206 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.5592. Min Act: -0.0000

Data Index: 681436 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.3770. Min Act: -0.0000

Data Index: 1712437 (The Pile)

Max Activating Token Index: 988

Text #5

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.3907. Min Act: -0.0000

Data Index: 702478 (The Pile)

Max Activating Token Index: 227

Text #6

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.3825. Min Act: -0.0000

Data Index: 878704 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.3664. Min Act: -0.0000

Data Index: 236766 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.4947. Min Act: -0.0000

Data Index: 276668 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.6273. Min Act: -0.0000

Data Index: 749572 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.4790. Min Act: -0.0000

Data Index: 42257 (The Pile)

Max Activating Token Index: 285

Text #11

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.3081. Min Act: -0.0000

Data Index: 1443024 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.5000. Min Act: -0.0000

Data Index: 1466134 (The Pile)

Max Activating Token Index: 916

Text #13

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.2654. Min Act: -0.0000

Data Index: 139603 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.6964. Min Act: -0.0000

Data Index: 1841051 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.3720. Min Act: -0.0000

Data Index: 1653272 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.6661. Min Act: -0.0000

Data Index: 1763938 (The Pile)

Max Activating Token Index: 836

Text #17

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.1133. Min Act: -0.0000

Data Index: 1921015 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.6058. Min Act: -0.0000

Data Index: 276569 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 4.7638. Min Range: -4.7638

Max Act: 2.9375. Min Act: -0.0000

Data Index: 1667659 (The Pile)

Max Activating Token Index: 916