Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3135 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0736. Min Act: -0.0003

Data Index: 759835 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1436968 (Python Code)

Max Activating Token Index: 894

Text #2

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0697. Min Act: -0.0003

Data Index: 227083 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0671. Min Act: -0.0003

Data Index: 61863 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0668. Min Act: -0.0003

Data Index: 313940 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1435179 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1146518 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0662. Min Act: -0.0003

Data Index: 478024 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0654. Min Act: -0.0003

Data Index: 795157 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0653. Min Act: -0.0003

Data Index: 392001 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1545471 (Python Code)

Max Activating Token Index: 587

Text #11

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0647. Min Act: -0.0002

Data Index: 727310 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0645. Min Act: -0.0003

Data Index: 633623 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0641. Min Act: -0.0003

Data Index: 742613 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0641. Min Act: -0.0003

Data Index: 433791 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0641. Min Act: -0.0003

Data Index: 604794 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0640. Min Act: -0.0003

Data Index: 578513 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0640. Min Act: -0.0003

Data Index: 139173 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0639. Min Act: -0.0003

Data Index: 675465 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1301140 (C4 (Web Text))

Max Activating Token Index: 951