Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1127 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0003

Data Index: 1492393 (Python Code)

Max Activating Token Index: 686

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0734. Min Act: -0.0003

Data Index: 677550 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1309274 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0639. Min Act: -0.0003

Data Index: 527948 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0660. Min Act: -0.0003

Data Index: 192707 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0616. Min Act: -0.0003

Data Index: 631460 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0595. Min Act: -0.0003

Data Index: 375742 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1439154 (Python Code)

Max Activating Token Index: 27

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0613. Min Act: -0.0003

Data Index: 991347 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0614. Min Act: -0.0003

Data Index: 841572 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1226749 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0578. Min Act: -0.0003

Data Index: 962323 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0607. Min Act: -0.0003

Data Index: 712594 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1443568 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0605. Min Act: -0.0004

Data Index: 1213067 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0591. Min Act: -0.0003

Data Index: 430658 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0598. Min Act: -0.0004

Data Index: 555013 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0566. Min Act: -0.0003

Data Index: 941404 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1551754 (Python Code)

Max Activating Token Index: 211

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1559979 (Python Code)

Max Activating Token Index: 293