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

Dataset: The Pile

Neuron 1165 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1473019 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.6169. Min Act: -0.0000

Data Index: 776629 (The Pile)

Max Activating Token Index: 710

Text #2

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1582352 (The Pile)

Max Activating Token Index: 795

Text #3

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5260. Min Act: -0.0000

Data Index: 410670 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5099. Min Act: -0.0000

Data Index: 999592 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5095. Min Act: -0.0000

Data Index: 652201 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5107. Min Act: -0.0000

Data Index: 924672 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1509354 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5278. Min Act: -0.0000

Data Index: 237874 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4343. Min Act: -0.0000

Data Index: 248142 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4619. Min Act: -0.0000

Data Index: 551968 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4788. Min Act: -0.0000

Data Index: 889435 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.3990. Min Act: -0.0000

Data Index: 840348 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1969621 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4144. Min Act: -0.0000

Data Index: 984704 (The Pile)

Max Activating Token Index: 778

Text #15

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.3658. Min Act: -0.0000

Data Index: 114689 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1366895 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1744393 (The Pile)

Max Activating Token Index: 773

Text #18

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4612. Min Act: -0.0000

Data Index: 682954 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.3243. Min Act: -0.0000

Data Index: 931544 (The Pile)

Max Activating Token Index: 637