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

Dataset: The Pile

Neuron 2020 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: 1.1876. Min Range: -1.1876

Max Act: 1.1876. Min Act: -0.0000

Data Index: 214065 (The Pile)

Max Activating Token Index: 31

Text #1

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.1261. Min Act: -0.0000

Data Index: 428427 (The Pile)

Max Activating Token Index: 235

Text #2

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.0863. Min Act: -0.0000

Data Index: 815868 (The Pile)

Max Activating Token Index: 566

Text #3

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1328643 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9794. Min Act: -0.0000

Data Index: 718604 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1173223 (The Pile)

Max Activating Token Index: 809

Text #6

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1508277 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1615473 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8176. Min Act: -0.0000

Data Index: 576418 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7976. Min Act: -0.0000

Data Index: 174396 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7662. Min Act: -0.0000

Data Index: 507022 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1125534 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1480006 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7431. Min Act: -0.0000

Data Index: 358809 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1710251 (The Pile)

Max Activating Token Index: 724

Text #15

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1284354 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.6846. Min Act: -0.0000

Data Index: 530735 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7211. Min Act: -0.0000

Data Index: 124242 (The Pile)

Max Activating Token Index: 645

Text #18

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1852527 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.7144. Min Act: -0.0000

Data Index: 430000 (The Pile)

Max Activating Token Index: 372