Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1372 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0798. Min Act: -0.0003

Data Index: 1564500 (Python Code)

Max Activating Token Index: 436

Text #1

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1632998 (Python Code)

Max Activating Token Index: 402

Text #2

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0724. Min Act: -0.0003

Data Index: 1561135 (Python Code)

Max Activating Token Index: 449

Text #3

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1401211 (Python Code)

Max Activating Token Index: 525

Text #4

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1547534 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1643566 (Python Code)

Max Activating Token Index: 732

Text #6

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1530189 (Python Code)

Max Activating Token Index: 382

Text #7

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1599967 (Python Code)

Max Activating Token Index: 295

Text #8

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1379542 (Python Code)

Max Activating Token Index: 862

Text #9

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0632. Min Act: -0.0003

Data Index: 1587409 (Python Code)

Max Activating Token Index: 954

Text #10

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1541126 (Python Code)

Max Activating Token Index: 235

Text #11

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1422934 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1152128 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1558799 (Python Code)

Max Activating Token Index: 292

Text #14

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0614. Min Act: -0.0003

Data Index: 1456476 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1612260 (Python Code)

Max Activating Token Index: 228

Text #16

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1503713 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1423449 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0596. Min Act: -0.0003

Data Index: 418420 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0591. Min Act: -0.0004

Data Index: 1174390 (C4 (Web Text))

Max Activating Token Index: 965