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

Dataset: The Pile

Neuron 905 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6596. Min Range: -3.6596

Max Act: 3.6596. Min Act: -0.0000

Data Index: 987475 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 3.6596. Min Range: -3.6596

Max Act: 3.5733. Min Act: -0.0000

Data Index: 1264580 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 3.6596. Min Range: -3.6596

Max Act: 3.2089. Min Act: -0.0000

Data Index: 475399 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.9598. Min Act: -0.0000

Data Index: 1276552 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.8181. Min Act: -0.0000

Data Index: 1492541 (The Pile)

Max Activating Token Index: 41

Text #5

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.7730. Min Act: -0.0000

Data Index: 1265915 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.8515. Min Act: -0.0000

Data Index: 670250 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.8184. Min Act: -0.0000

Data Index: 1013978 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.4994. Min Act: -0.0000

Data Index: 1767773 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.3758. Min Act: -0.0000

Data Index: 94932 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.4971. Min Act: -0.0000

Data Index: 1234276 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.4442. Min Act: -0.0000

Data Index: 974992 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.4488. Min Act: -0.0000

Data Index: 1285879 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.5701. Min Act: -0.0000

Data Index: 912431 (The Pile)

Max Activating Token Index: 214

Text #14

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.4276. Min Act: -0.0000

Data Index: 289350 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.1747. Min Act: -0.0000

Data Index: 1685547 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.3910. Min Act: -0.0000

Data Index: 256280 (The Pile)

Max Activating Token Index: 118

Text #17

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.2730. Min Act: -0.0000

Data Index: 709205 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.2750. Min Act: -0.0000

Data Index: 704384 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 3.6596. Min Range: -3.6596

Max Act: 2.2653. Min Act: -0.0000

Data Index: 888740 (The Pile)

Max Activating Token Index: 821