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

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

Neuron 251 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.4666. Min Act: 0.0000

Data Index: 706789 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1153356 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3920. Min Act: -0.0000

Data Index: 286931 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1316865 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3408. Min Act: 0.0000

Data Index: 787175 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3599. Min Act: 0.0000

Data Index: 776548 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3237. Min Act: 0.0001

Data Index: 722471 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3008. Min Act: -0.0000

Data Index: 516458 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3211. Min Act: -0.0000

Data Index: 286067 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3184. Min Act: 0.0001

Data Index: 406920 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2907. Min Act: -0.0000

Data Index: 800509 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2790. Min Act: 0.0001

Data Index: 755588 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2767. Min Act: -0.0000

Data Index: 990949 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2809. Min Act: 0.0000

Data Index: 205391 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2898. Min Act: -0.0000

Data Index: 28527 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2751. Min Act: -0.0000

Data Index: 878421 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1351848 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2791. Min Act: 0.0001

Data Index: 1298693 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2703. Min Act: 0.0000

Data Index: 412950 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.2658. Min Act: 0.0000

Data Index: 1092305 (C4 (Web Text))

Max Activating Token Index: 482