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

Dataset: The Pile

Neuron 2803 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1843. Min Act: -0.0000

Data Index: 837003 (The Pile)

Max Activating Token Index: 426

Text #1

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.9110. Min Act: -0.0000

Data Index: 443425 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.0896. Min Act: -0.0000

Data Index: 1175450 (The Pile)

Max Activating Token Index: 937

Text #3

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.5152. Min Act: -0.0000

Data Index: 1123685 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.1445. Min Act: -0.0000

Data Index: 896932 (The Pile)

Max Activating Token Index: 179

Text #5

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.4414. Min Act: -0.0000

Data Index: 614814 (The Pile)

Max Activating Token Index: 353

Text #6

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.8590. Min Act: -0.0000

Data Index: 1133014 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.1274. Min Act: -0.0000

Data Index: 1193335 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.2331. Min Act: -0.0000

Data Index: 1476065 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.0600. Min Act: -0.0000

Data Index: 1339852 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.1589. Min Act: -0.0000

Data Index: 1180915 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.2094. Min Act: -0.0000

Data Index: 654712 (The Pile)

Max Activating Token Index: 672

Text #12

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.4531. Min Act: -0.0000

Data Index: 1493115 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 3.1843. Min Range: -3.1843

Max Act: 1.9628. Min Act: -0.0000

Data Index: 1501692 (The Pile)

Max Activating Token Index: 18

Text #14

Max Range: 3.1843. Min Range: -3.1843

Max Act: 1.9128. Min Act: -0.0000

Data Index: 701688 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 3.1843. Min Range: -3.1843

Max Act: 2.0891. Min Act: -0.0000

Data Index: 536040 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 3.1843. Min Range: -3.1843

Max Act: 1.8667. Min Act: -0.0000

Data Index: 335352 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 3.1843. Min Range: -3.1843

Max Act: 1.8595. Min Act: -0.0000

Data Index: 1481368 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 3.1843. Min Range: -3.1843

Max Act: 1.9358. Min Act: -0.0000

Data Index: 1061968 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 3.1843. Min Range: -3.1843

Max Act: 1.9655. Min Act: -0.0000

Data Index: 978818 (The Pile)

Max Activating Token Index: 17