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

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

Neuron 4995 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.4853. Min Act: -0.0001

Data Index: 25893 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.9484. Min Act: -0.0001

Data Index: 555009 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.6076. Min Act: -0.0001

Data Index: 809542 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.7410. Min Act: -0.0001

Data Index: 676537 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.7889. Min Act: -0.0001

Data Index: 264504 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.5091. Min Act: -0.0001

Data Index: 517458 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.4725. Min Act: -0.0000

Data Index: 660909 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.6391. Min Act: -0.0001

Data Index: 214595 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.4010. Min Act: -0.0001

Data Index: 384355 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.3705. Min Act: -0.0000

Data Index: 801505 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.5016. Min Act: -0.0000

Data Index: 923102 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.5071. Min Act: -0.0001

Data Index: 3669 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.1534. Min Act: -0.0000

Data Index: 850816 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.2523. Min Act: -0.0000

Data Index: 708844 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.1220. Min Act: -0.0001

Data Index: 1552816 (Python Code)

Max Activating Token Index: 416

Text #15

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.1031. Min Act: -0.0000

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.2547. Min Act: -0.0001

Data Index: 549353 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.2534. Min Act: -0.0001

Data Index: 888734 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 3.9484. Min Range: -3.9484

Max Act: 3.1074. Min Act: -0.0001

Data Index: 962484 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 3.9484. Min Range: -3.9484

Max Act: 2.9373. Min Act: -0.0001

Data Index: 361811 (C4 (Web Text))

Max Activating Token Index: 216