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

Dataset: The Pile

Neuron 2624 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: 1.4242. Min Range: -1.4242

Max Act: 1.4242. Min Act: -0.0000

Data Index: 1404167 (The Pile)

Max Activating Token Index: 829

Text #1

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2321. Min Act: -0.0000

Data Index: 214113 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2969. Min Act: -0.0000

Data Index: 1555725 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1972048 (The Pile)

Max Activating Token Index: 302

Text #4

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2734. Min Act: -0.0000

Data Index: 1376472 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2052. Min Act: -0.0000

Data Index: 367487 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1986155 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1654. Min Act: -0.0000

Data Index: 951370 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0713. Min Act: -0.0000

Data Index: 784923 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1322. Min Act: -0.0000

Data Index: 264724 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 1.4242. Min Range: -1.4242

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1861013 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0332. Min Act: -0.0000

Data Index: 509315 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0313. Min Act: -0.0000

Data Index: 1502082 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0280. Min Act: -0.0000

Data Index: 656554 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 1.4242. Min Range: -1.4242

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1218631 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0520. Min Act: -0.0000

Data Index: 412624 (The Pile)

Max Activating Token Index: 702

Text #16

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0118. Min Act: -0.0000

Data Index: 801674 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 1.4242. Min Range: -1.4242

Max Act: 0.9468. Min Act: -0.0000

Data Index: 172431 (The Pile)

Max Activating Token Index: 756

Text #18

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0135. Min Act: -0.0000

Data Index: 185312 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 1.4242. Min Range: -1.4242

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1577403 (The Pile)

Max Activating Token Index: 621