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

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

Neuron 4004 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1618900 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1587358 (Python Code)

Max Activating Token Index: 599

Text #2

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1436382 (Python Code)

Max Activating Token Index: 312

Text #3

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0743. Min Act: -0.0000

Data Index: 190141 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1393113 (Python Code)

Max Activating Token Index: 243

Text #5

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1464651 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1653451 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1208187 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1454955 (Python Code)

Max Activating Token Index: 619

Text #9

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1424496 (Python Code)

Max Activating Token Index: 300

Text #10

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1508904 (Python Code)

Max Activating Token Index: 202

Text #11

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1554670 (Python Code)

Max Activating Token Index: 688

Text #12

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1519061 (Python Code)

Max Activating Token Index: 950

Text #13

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1153969 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1231504 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1458393 (Python Code)

Max Activating Token Index: 993

Text #16

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1425063 (Python Code)

Max Activating Token Index: 498

Text #17

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1420588 (Python Code)

Max Activating Token Index: 246

Text #18

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0669. Min Act: 0.0000

Data Index: 1404174 (Python Code)

Max Activating Token Index: 892

Text #19

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1653825 (Python Code)

Max Activating Token Index: 361