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

Dataset: The Pile

Neuron 2242 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: 1.8366. Min Range: -1.8366

Max Act: 1.7488. Min Act: -0.0000

Data Index: 463893 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.7484. Min Act: -0.0000

Data Index: 961280 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.6178. Min Act: -0.0000

Data Index: 958754 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.7755. Min Act: -0.0000

Data Index: 724684 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.8366. Min Act: -0.0000

Data Index: 274378 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.5488. Min Act: -0.0000

Data Index: 842028 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.5677. Min Act: -0.0000

Data Index: 1142903 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.5795. Min Act: -0.0000

Data Index: 471025 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.4232. Min Act: -0.0000

Data Index: 391722 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.4931. Min Act: -0.0000

Data Index: 339177 (The Pile)

Max Activating Token Index: 745

Text #10

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.4955. Min Act: -0.0000

Data Index: 1787606 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.6549. Min Act: -0.0000

Data Index: 1178621 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.3925. Min Act: -0.0000

Data Index: 746726 (The Pile)

Max Activating Token Index: 160

Text #13

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1851986 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.5668. Min Act: -0.0000

Data Index: 1045117 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.6062. Min Act: -0.0000

Data Index: 1600927 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.4454. Min Act: -0.0000

Data Index: 777505 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.4514. Min Act: -0.0000

Data Index: 554052 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.6244. Min Act: -0.0000

Data Index: 507493 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 1.8366. Min Range: -1.8366

Max Act: 1.5176. Min Act: -0.0000

Data Index: 87067 (The Pile)

Max Activating Token Index: 490