Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 222 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0748. Min Act: -0.0001

Data Index: 862637 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0673. Min Act: -0.0001

Data Index: 486100 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0649. Min Act: -0.0001

Data Index: 308930 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0654. Min Act: -0.0001

Data Index: 901729 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0639. Min Act: -0.0002

Data Index: 66239 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0578. Min Act: -0.0001

Data Index: 666959 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0621. Min Act: -0.0002

Data Index: 805735 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0639. Min Act: -0.0002

Data Index: 554857 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1187328 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0623. Min Act: -0.0002

Data Index: 883234 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0645. Min Act: -0.0001

Data Index: 475147 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0557. Min Act: -0.0001

Data Index: 252651 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1015315 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0577. Min Act: -0.0002

Data Index: 486597 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0568. Min Act: -0.0002

Data Index: 681403 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1348906 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0592. Min Act: -0.0001

Data Index: 453620 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0537. Min Act: -0.0001

Data Index: 255904 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1291819 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0546. Min Act: -0.0001

Data Index: 550388 (C4 (Web Text))

Max Activating Token Index: 95