Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2459 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1458373 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1586075 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1608488 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3895. Min Act: -0.0000

Data Index: 421603 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1913427 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3775. Min Act: -0.0000

Data Index: 381975 (The Pile)

Max Activating Token Index: 863

Text #6

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3727. Min Act: -0.0000

Data Index: 451522 (The Pile)

Max Activating Token Index: 379

Text #7

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1809108 (The Pile)

Max Activating Token Index: 867

Text #8

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3561. Min Act: -0.0000

Data Index: 227376 (The Pile)

Max Activating Token Index: 513

Text #9

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1571064 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3329. Min Act: -0.0000

Data Index: 693180 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3519. Min Act: -0.0000

Data Index: 353572 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3381. Min Act: -0.0000

Data Index: 708654 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3488. Min Act: -0.0000

Data Index: 656662 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3289. Min Act: -0.0000

Data Index: 971842 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1925851 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3289. Min Act: -0.0000

Data Index: 858345 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1335724 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1019593 (The Pile)

Max Activating Token Index: 830

Text #19

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3393. Min Act: -0.0000

Data Index: 244176 (The Pile)

Max Activating Token Index: 473