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

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

Neuron 1233 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1349949 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1225820 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0708. Min Act: -0.0000

Data Index: 105769 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0703. Min Act: -0.0000

Data Index: 631193 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0778. Min Act: -0.0000

Data Index: 164363 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0664. Min Act: -0.0000

Data Index: 158396 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0654. Min Act: -0.0000

Data Index: 262237 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0663. Min Act: -0.0000

Data Index: 614021 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0661. Min Act: -0.0001

Data Index: 450808 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1127071 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0621. Min Act: -0.0000

Data Index: 85233 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1258041 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0603. Min Act: -0.0001

Data Index: 615865 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0619. Min Act: -0.0000

Data Index: 1312926 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1029473 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0559. Min Act: -0.0000

Data Index: 216974 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0604. Min Act: -0.0000

Data Index: 393547 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0595. Min Act: -0.0000

Data Index: 525273 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0616. Min Act: -0.0000

Data Index: 526432 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0597. Min Act: -0.0000

Data Index: 361492 (C4 (Web Text))

Max Activating Token Index: 911