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

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

Neuron 1988 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0003

Data Index: 984991 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0656. Min Act: -0.0003

Data Index: 341064 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1228210 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1116729 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0662. Min Act: -0.0003

Data Index: 378956 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0587. Min Act: -0.0003

Data Index: 705960 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0630. Min Act: -0.0003

Data Index: 145199 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1043093 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0612. Min Act: -0.0003

Data Index: 770012 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0634. Min Act: -0.0003

Data Index: 755014 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1263202 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0604. Min Act: -0.0003

Data Index: 765235 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0641. Min Act: -0.0003

Data Index: 125224 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0599. Min Act: -0.0003

Data Index: 389944 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0594. Min Act: -0.0003

Data Index: 692782 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0647. Min Act: -0.0003

Data Index: 431327 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0623. Min Act: -0.0003

Data Index: 766426 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1105032 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1254204 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0530. Min Act: -0.0003

Data Index: 554145 (C4 (Web Text))

Max Activating Token Index: 19