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

Dataset: The Pile

Neuron 4595 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: 0.9524. Min Range: -0.9524

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1786159 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1308283 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1438463 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6067. Min Act: -0.0000

Data Index: 758288 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1271703 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1619765 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5874. Min Act: -0.0000

Data Index: 368725 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1362170 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1620771 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1118417 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1798484 (The Pile)

Max Activating Token Index: 941

Text #11

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.4885. Min Act: -0.0000

Data Index: 237268 (The Pile)

Max Activating Token Index: 101

Text #12

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1579740 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1955635 (The Pile)

Max Activating Token Index: 1008

Text #14

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1404575 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.4533. Min Act: -0.0000

Data Index: 703076 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1902431 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1316705 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1525569 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 0.9524. Min Range: -0.9524

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1158904 (The Pile)

Max Activating Token Index: 929