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

Dataset: The Pile

Neuron 2971 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: 1.2279. Min Range: -1.2279

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1206759 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 1.2279. Min Range: -1.2279

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1029487 (The Pile)

Max Activating Token Index: 983

Text #2

Max Range: 1.2279. Min Range: -1.2279

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1718274 (The Pile)

Max Activating Token Index: 914

Text #3

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1085373 (The Pile)

Max Activating Token Index: 800

Text #4

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1201632 (The Pile)

Max Activating Token Index: 927

Text #5

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1754706 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 1.2279. Min Range: -1.2279

Max Act: 1.0073. Min Act: -0.0000

Data Index: 466289 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1738087 (The Pile)

Max Activating Token Index: 860

Text #8

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.8711. Min Act: -0.0000

Data Index: 523864 (The Pile)

Max Activating Token Index: 956

Text #9

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1602730 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.7369. Min Act: -0.0000

Data Index: 149925 (The Pile)

Max Activating Token Index: 988

Text #11

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1729711 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1191110 (The Pile)

Max Activating Token Index: 887

Text #13

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1683472 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.7370. Min Act: -0.0000

Data Index: 69438 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.8171. Min Act: -0.0000

Data Index: 985252 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1157491 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.7521. Min Act: -0.0000

Data Index: 760989 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1750029 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 1.2279. Min Range: -1.2279

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1958081 (The Pile)

Max Activating Token Index: 928