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

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

Neuron 2115 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8891. Min Range: -3.8891

Max Act: 3.8891. Min Act: -0.0000

Data Index: 104281 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 3.8891. Min Range: -3.8891

Max Act: 3.4985. Min Act: -0.0000

Data Index: 469378 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 3.8891. Min Range: -3.8891

Max Act: 3.0617. Min Act: -0.0000

Data Index: 1226363 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.8169. Min Act: -0.0000

Data Index: 451990 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.9616. Min Act: -0.0000

Data Index: 218303 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.5353. Min Act: -0.0000

Data Index: 828307 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.5263. Min Act: -0.0000

Data Index: 895796 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.6509. Min Act: -0.0000

Data Index: 961 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.4680. Min Act: -0.0000

Data Index: 831565 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.4229. Min Act: -0.0000

Data Index: 179743 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.5640. Min Act: -0.0000

Data Index: 914350 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.4023. Min Act: -0.0000

Data Index: 1219616 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.3439. Min Act: -0.0000

Data Index: 301663 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.5703. Min Act: -0.0000

Data Index: 10846 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.4208. Min Act: -0.0000

Data Index: 1216019 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.4099. Min Act: -0.0000

Data Index: 715045 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.4183. Min Act: -0.0000

Data Index: 1307612 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.2895. Min Act: -0.0000

Data Index: 961866 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.4019. Min Act: -0.0000

Data Index: 1101068 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 3.8891. Min Range: -3.8891

Max Act: 2.3670. Min Act: -0.0000

Data Index: 1041772 (C4 (Web Text))

Max Activating Token Index: 717