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

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

Neuron 2258 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0002

Data Index: 189156 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1125083 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1450114 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0653. Min Act: -0.0002

Data Index: 220985 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1530939 (Python Code)

Max Activating Token Index: 588

Text #5

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1387178 (Python Code)

Max Activating Token Index: 557

Text #6

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1654428 (Python Code)

Max Activating Token Index: 878

Text #7

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1419004 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1379035 (Python Code)

Max Activating Token Index: 440

Text #9

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1450006 (Python Code)

Max Activating Token Index: 714

Text #10

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1396743 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1481170 (Python Code)

Max Activating Token Index: 276

Text #12

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1483152 (Python Code)

Max Activating Token Index: 69

Text #13

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1476862 (Python Code)

Max Activating Token Index: 440

Text #14

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1472233 (Python Code)

Max Activating Token Index: 651

Text #15

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1088097 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0547. Min Act: -0.0002

Data Index: 559335 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1551803 (Python Code)

Max Activating Token Index: 511

Text #18

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1009886 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1031104 (C4 (Web Text))

Max Activating Token Index: 850