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

Dataset: The Pile

Neuron 528 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: 1.5846. Min Range: -1.5846

Max Act: 1.5846. Min Act: -0.0000

Data Index: 686122 (The Pile)

Max Activating Token Index: 294

Text #1

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.5628. Min Act: -0.0000

Data Index: 694645 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.5398. Min Act: -0.0000

Data Index: 1674644 (The Pile)

Max Activating Token Index: 832

Text #3

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.4294. Min Act: -0.0000

Data Index: 726714 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.4102. Min Act: -0.0000

Data Index: 697366 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.5271. Min Act: -0.0000

Data Index: 673124 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.4475. Min Act: -0.0000

Data Index: 533706 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.3467. Min Act: -0.0000

Data Index: 231641 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.4325. Min Act: -0.0000

Data Index: 19371 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.4255. Min Act: -0.0000

Data Index: 763993 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.3316. Min Act: -0.0000

Data Index: 1873647 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1840197 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.3988. Min Act: -0.0000

Data Index: 473348 (The Pile)

Max Activating Token Index: 267

Text #13

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.3434. Min Act: -0.0000

Data Index: 1685075 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.1835. Min Act: -0.0000

Data Index: 443458 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.2988. Min Act: -0.0000

Data Index: 194013 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.2934. Min Act: -0.0000

Data Index: 1477064 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.3689. Min Act: -0.0000

Data Index: 849429 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.4395. Min Act: -0.0000

Data Index: 1018791 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.3442. Min Act: -0.0000

Data Index: 84099 (The Pile)

Max Activating Token Index: 623