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

Dataset: The Pile

Neuron 1835 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: 1.8104. Min Range: -1.8104

Max Act: 1.8104. Min Act: -0.0000

Data Index: 300062 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7557. Min Act: -0.0000

Data Index: 92 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.5644. Min Act: -0.0000

Data Index: 644375 (The Pile)

Max Activating Token Index: 845

Text #3

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.5331. Min Act: -0.0000

Data Index: 503445 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.3269. Min Act: -0.0000

Data Index: 557415 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4715. Min Act: -0.0000

Data Index: 1947110 (The Pile)

Max Activating Token Index: 326

Text #6

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4319. Min Act: -0.0000

Data Index: 1042019 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.5039. Min Act: -0.0000

Data Index: 1967182 (The Pile)

Max Activating Token Index: 716

Text #8

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1625688 (The Pile)

Max Activating Token Index: 679

Text #9

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1276671 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.3360. Min Act: -0.0000

Data Index: 1172156 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7192. Min Act: -0.0000

Data Index: 866395 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4599. Min Act: -0.0000

Data Index: 979319 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4415. Min Act: -0.0000

Data Index: 178158 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1805403 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.3532. Min Act: -0.0000

Data Index: 392649 (The Pile)

Max Activating Token Index: 468

Text #16

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.3791. Min Act: -0.0000

Data Index: 90677 (The Pile)

Max Activating Token Index: 683

Text #17

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.3011. Min Act: -0.0000

Data Index: 698952 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.3652. Min Act: -0.0000

Data Index: 1280534 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.5401. Min Act: -0.0000

Data Index: 321804 (The Pile)

Max Activating Token Index: 948