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

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

Neuron 3607 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.2134. Min Act: -0.0001

Data Index: 834761 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.2009. Min Act: -0.0001

Data Index: 393668 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1963. Min Act: -0.0001

Data Index: 281920 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1303096 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1833. Min Act: -0.0001

Data Index: 197997 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1735. Min Act: -0.0001

Data Index: 80869 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1768. Min Act: -0.0001

Data Index: 102388 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1790. Min Act: -0.0001

Data Index: 295903 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1912. Min Act: -0.0001

Data Index: 254861 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1683. Min Act: -0.0001

Data Index: 959695 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1755. Min Act: -0.0001

Data Index: 797686 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1634. Min Act: -0.0001

Data Index: 149492 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1680. Min Act: -0.0001

Data Index: 698677 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1120316 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1054297 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1557. Min Act: -0.0001

Data Index: 753771 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1587. Min Act: -0.0001

Data Index: 862836 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1631. Min Act: -0.0001

Data Index: 809482 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1683. Min Act: -0.0001

Data Index: 208640 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1574. Min Act: -0.0001

Data Index: 301215 (C4 (Web Text))

Max Activating Token Index: 593