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

Dataset: The Pile

Neuron 757 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.6531. Min Act: -0.0001

Data Index: 1432792 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.6682. Min Act: -0.0001

Data Index: 1349269 (The Pile)

Max Activating Token Index: 913

Text #2

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.6650. Min Act: -0.0000

Data Index: 39746 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1944800 (The Pile)

Max Activating Token Index: 857

Text #4

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.6147. Min Act: -0.0000

Data Index: 855772 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.6162. Min Act: -0.0001

Data Index: 1266870 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5793. Min Act: -0.0000

Data Index: 173782 (The Pile)

Max Activating Token Index: 498

Text #7

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1364051 (The Pile)

Max Activating Token Index: 376

Text #8

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5434. Min Act: -0.0000

Data Index: 842209 (The Pile)

Max Activating Token Index: 810

Text #9

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5744. Min Act: -0.0000

Data Index: 44455 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1149188 (The Pile)

Max Activating Token Index: 816

Text #11

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1687600 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1491359 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5336. Min Act: -0.0000

Data Index: 403003 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1334899 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5148. Min Act: -0.0000

Data Index: 589339 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5138. Min Act: -0.0000

Data Index: 968810 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5331. Min Act: -0.0000

Data Index: 862799 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1387609 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 0.6682. Min Range: -0.6682

Max Act: 0.5255. Min Act: -0.0001

Data Index: 1563020 (The Pile)

Max Activating Token Index: 270