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

Dataset: The Pile

Neuron 896 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: 0.6875. Min Range: -0.6875

Max Act: 0.6590. Min Act: -0.0000

Data Index: 276613 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6775. Min Act: -0.0000

Data Index: 584169 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5822. Min Act: -0.0000

Data Index: 542085 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1347125 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1213728 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5787. Min Act: -0.0000

Data Index: 506431 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5954. Min Act: -0.0001

Data Index: 1884975 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1001690 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6051. Min Act: -0.0000

Data Index: 445146 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1529837 (The Pile)

Max Activating Token Index: 890

Text #10

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1098758 (The Pile)

Max Activating Token Index: 880

Text #11

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1881410 (The Pile)

Max Activating Token Index: 657

Text #12

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6182. Min Act: -0.0000

Data Index: 444984 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1044949 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5628. Min Act: -0.0001

Data Index: 404746 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1441384 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1484605 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1800630 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5360. Min Act: -0.0000

Data Index: 850006 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1581531 (The Pile)

Max Activating Token Index: 333