Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1942 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4806. Min Range: -3.4806

Max Act: 3.4806. Min Act: -0.0000

Data Index: 263707 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 3.4806. Min Range: -3.4806

Max Act: 3.2875. Min Act: -0.0000

Data Index: 774757 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 3.4806. Min Range: -3.4806

Max Act: 3.3545. Min Act: -0.0000

Data Index: 598608 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.5531. Min Act: -0.0000

Data Index: 837295 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.7309. Min Act: -0.0000

Data Index: 1164221 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.8692. Min Act: -0.0000

Data Index: 636771 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.5569. Min Act: -0.0000

Data Index: 715688 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.3994. Min Act: -0.0000

Data Index: 375935 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.5841. Min Act: -0.0000

Data Index: 877242 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.4115. Min Act: -0.0000

Data Index: 835395 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.4118. Min Act: -0.0000

Data Index: 778766 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.4258. Min Act: -0.0000

Data Index: 362640 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.5151. Min Act: -0.0000

Data Index: 956193 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.3920. Min Act: -0.0000

Data Index: 856344 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.5690. Min Act: -0.0000

Data Index: 934389 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.4033. Min Act: -0.0000

Data Index: 968524 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.5015. Min Act: -0.0000

Data Index: 989263 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.3296. Min Act: -0.0000

Data Index: 948230 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.3254. Min Act: -0.0000

Data Index: 875999 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 3.4806. Min Range: -3.4806

Max Act: 2.3194. Min Act: -0.0000

Data Index: 748107 (C4 (Web Text))

Max Activating Token Index: 322