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

Dataset: The Pile

Neuron 4043 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1825121 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1783740 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.1065. Min Act: -0.0000

Data Index: 315037 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1337869 (The Pile)

Max Activating Token Index: 244

Text #4

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9722. Min Act: -0.0000

Data Index: 436505 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9152. Min Act: -0.0000

Data Index: 784118 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.8775. Min Act: -0.0000

Data Index: 940337 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7619. Min Act: -0.0000

Data Index: 540565 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7513. Min Act: -0.0000

Data Index: 514606 (The Pile)

Max Activating Token Index: 172

Text #9

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1580069 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7101. Min Act: -0.0000

Data Index: 571379 (The Pile)

Max Activating Token Index: 436

Text #11

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1256856 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1686967 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1461622 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1634933 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1982089 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7928. Min Act: -0.0000

Data Index: 740171 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1234212 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7575. Min Act: -0.0000

Data Index: 626508 (The Pile)

Max Activating Token Index: 317

Text #19

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1708973 (The Pile)

Max Activating Token Index: 842