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

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

Neuron 2689 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1685. Min Range: -1.1685

Max Act: 1.1685. Min Act: -0.0000

Data Index: 375127 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.8762. Min Act: -0.0000

Data Index: 306110 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.7451. Min Act: -0.0000

Data Index: 551858 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.7801. Min Act: -0.0000

Data Index: 453833 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1323898 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.6766. Min Act: -0.0000

Data Index: 230689 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1040586 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.6654. Min Act: -0.0000

Data Index: 18503 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.7340. Min Act: -0.0000

Data Index: 751359 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1356147 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.6388. Min Act: -0.0000

Data Index: 29756 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.6307. Min Act: -0.0000

Data Index: 454796 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1146564 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.5761. Min Act: -0.0000

Data Index: 596555 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.5955. Min Act: -0.0000

Data Index: 823316 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.5672. Min Act: -0.0000

Data Index: 375130 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.5284. Min Act: -0.0000

Data Index: 154240 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.5443. Min Act: -0.0000

Data Index: 532563 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.5664. Min Act: -0.0000

Data Index: 287043 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 1.1685. Min Range: -1.1685

Max Act: 0.5142. Min Act: -0.0000

Data Index: 708282 (C4 (Web Text))

Max Activating Token Index: 658