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

Dataset: The Pile

Neuron 4213 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: 3.4090. Min Range: -3.4090

Max Act: 3.3526. Min Act: -0.0000

Data Index: 1983164 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.4090. Min Act: -0.0000

Data Index: 334258 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.0259. Min Act: -0.0000

Data Index: 1156885 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1272. Min Act: -0.0000

Data Index: 332904 (The Pile)

Max Activating Token Index: 745

Text #4

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.9618. Min Act: -0.0000

Data Index: 1967742 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.8641. Min Act: -0.0000

Data Index: 881025 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.6674. Min Act: -0.0000

Data Index: 1412180 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.7756. Min Act: -0.0000

Data Index: 1482631 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.6896. Min Act: -0.0000

Data Index: 1580679 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.6446. Min Act: -0.0000

Data Index: 158280 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.5236. Min Act: -0.0000

Data Index: 1945536 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.3871. Min Act: -0.0000

Data Index: 1461239 (The Pile)

Max Activating Token Index: 719

Text #12

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.5989. Min Act: -0.0000

Data Index: 850821 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.5901. Min Act: -0.0000

Data Index: 1710831 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.5407. Min Act: -0.0000

Data Index: 1805443 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.4828. Min Act: -0.0000

Data Index: 800897 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.6120. Min Act: -0.0000

Data Index: 757778 (The Pile)

Max Activating Token Index: 872

Text #17

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.4853. Min Act: -0.0000

Data Index: 1366354 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.4888. Min Act: -0.0000

Data Index: 336770 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 3.4090. Min Range: -3.4090

Max Act: 2.3020. Min Act: -0.0000

Data Index: 1358029 (The Pile)

Max Activating Token Index: 92