Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2556 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0574. Min Act: -0.0001

Data Index: 713659 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0784. Min Act: -0.0001

Data Index: 809643 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0809. Min Act: -0.0001

Data Index: 617088 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1338201 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0718. Min Act: -0.0001

Data Index: 576890 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0737. Min Act: -0.0001

Data Index: 902 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0705. Min Act: -0.0001

Data Index: 210675 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1335851 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0687. Min Act: -0.0001

Data Index: 397738 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0669. Min Act: -0.0001

Data Index: 223027 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0694. Min Act: -0.0001

Data Index: 325065 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0720. Min Act: -0.0001

Data Index: 461739 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0692. Min Act: -0.0001

Data Index: 197567 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1033046 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0691. Min Act: -0.0001

Data Index: 152322 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0664. Min Act: -0.0001

Data Index: 387347 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0637. Min Act: -0.0001

Data Index: 565756 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0612. Min Act: -0.0001

Data Index: 180054 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0638. Min Act: -0.0001

Data Index: 593593 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0657. Min Act: -0.0001

Data Index: 422073 (C4 (Web Text))

Max Activating Token Index: 88