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

Dataset: The Pile

Neuron 2212 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1210. Min Range: -1.1210

Max Act: 1.1210. Min Act: -0.0000

Data Index: 550410 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9359. Min Act: -0.0000

Data Index: 774874 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9432. Min Act: -0.0000

Data Index: 992841 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9048. Min Act: -0.0000

Data Index: 252032 (The Pile)

Max Activating Token Index: 571

Text #4

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1232023 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1751789 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8136. Min Act: -0.0000

Data Index: 755227 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1808963 (The Pile)

Max Activating Token Index: 763

Text #8

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8379. Min Act: -0.0000

Data Index: 685345 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1820617 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7895. Min Act: -0.0000

Data Index: 613665 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8246. Min Act: -0.0000

Data Index: 878232 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7904. Min Act: -0.0000

Data Index: 209092 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1864478 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1502912 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8087. Min Act: -0.0000

Data Index: 750523 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7589. Min Act: -0.0000

Data Index: 261198 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1548768 (The Pile)

Max Activating Token Index: 349

Text #18

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7999. Min Act: -0.0000

Data Index: 486970 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7314. Min Act: -0.0000

Data Index: 288290 (The Pile)

Max Activating Token Index: 977