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

Dataset: The Pile

Neuron 2381 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3121. Min Range: -1.3121

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1248288 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 1.3121. Min Range: -1.3121

Max Act: 1.0549. Min Act: -0.0000

Data Index: 795691 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1256200 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9386. Min Act: -0.0000

Data Index: 133255 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8919. Min Act: -0.0000

Data Index: 423045 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9316. Min Act: -0.0000

Data Index: 4217 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8562. Min Act: 0.0000

Data Index: 1053584 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1728886 (The Pile)

Max Activating Token Index: 418

Text #8

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1293744 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1442961 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1105867 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1549831 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8367. Min Act: -0.0000

Data Index: 820040 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8004. Min Act: -0.0000

Data Index: 426308 (The Pile)

Max Activating Token Index: 653

Text #14

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8308. Min Act: -0.0000

Data Index: 695916 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8427. Min Act: -0.0000

Data Index: 871794 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1995031 (The Pile)

Max Activating Token Index: 539

Text #17

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1166520 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.8382. Min Act: -0.0000

Data Index: 790205 (The Pile)

Max Activating Token Index: 894

Text #19

Max Range: 1.3121. Min Range: -1.3121

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1632417 (The Pile)

Max Activating Token Index: 758