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

Dataset: The Pile

Neuron 2430 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: 1.7142. Min Range: -1.7142

Max Act: 1.7142. Min Act: -0.0000

Data Index: 1003958 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1002728 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1788937 (The Pile)

Max Activating Token Index: 496

Text #3

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.7604. Min Act: -0.0000

Data Index: 49930 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.8092. Min Act: -0.0000

Data Index: 956011 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.7222. Min Act: -0.0000

Data Index: 729161 (The Pile)

Max Activating Token Index: 120

Text #6

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.6593. Min Act: -0.0000

Data Index: 584702 (The Pile)

Max Activating Token Index: 311

Text #7

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1990905 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1359243 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.6066. Min Act: -0.0000

Data Index: 133517 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.6713. Min Act: -0.0000

Data Index: 915376 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1118442 (The Pile)

Max Activating Token Index: 358

Text #12

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.6735. Min Act: -0.0000

Data Index: 407313 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.5983. Min Act: -0.0000

Data Index: 720073 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.5888. Min Act: -0.0000

Data Index: 579919 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.5499. Min Act: -0.0000

Data Index: 446777 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.5436. Min Act: -0.0000

Data Index: 171841 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1119361 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1945222 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 1.7142. Min Range: -1.7142

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1770612 (The Pile)

Max Activating Token Index: 855