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

Dataset: The Pile

Neuron 4248 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: 0.6707. Min Range: -0.6707

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1942190 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6621. Min Act: -0.0000

Data Index: 123976 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5836. Min Act: -0.0000

Data Index: 920363 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5743. Min Act: -0.0000

Data Index: 399205 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6033. Min Act: -0.0000

Data Index: 298825 (The Pile)

Max Activating Token Index: 909

Text #5

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1176708 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1950103 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5399. Min Act: -0.0000

Data Index: 560530 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.6031. Min Act: -0.0000

Data Index: 137607 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1077208 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1561050 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5434. Min Act: -0.0000

Data Index: 655039 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5315. Min Act: -0.0000

Data Index: 888070 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1763388 (The Pile)

Max Activating Token Index: 146

Text #14

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5012. Min Act: -0.0000

Data Index: 513589 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1114198 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5320. Min Act: -0.0000

Data Index: 97788 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4790. Min Act: -0.0000

Data Index: 809945 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1374128 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1072829 (The Pile)

Max Activating Token Index: 862