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

Dataset: The Pile

Neuron 3780 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.2198. Min Act: 0.0000

Data Index: 288687 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0113. Min Act: 0.0000

Data Index: 1563203 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9707. Min Act: -0.0000

Data Index: 614239 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9337. Min Act: -0.0000

Data Index: 581369 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1490702 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1178861 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1116882 (The Pile)

Max Activating Token Index: 324

Text #7

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1974445 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.7562. Min Act: -0.0000

Data Index: 625619 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.7221. Min Act: -0.0000

Data Index: 168679 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8092. Min Act: -0.0000

Data Index: 774415 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.6701. Min Act: -0.0000

Data Index: 709759 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.6410. Min Act: 0.0000

Data Index: 940250 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1533767 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1277252 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.6075. Min Act: 0.0000

Data Index: 1295405 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.5872. Min Act: -0.0000

Data Index: 758371 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1372122 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1304075 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.6521. Min Act: -0.0000

Data Index: 820163 (The Pile)

Max Activating Token Index: 983