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

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

Neuron 2310 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0709. Min Act: -0.0001

Data Index: 690654 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1463219 (Python Code)

Max Activating Token Index: 507

Text #2

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0709. Min Act: -0.0002

Data Index: 451256 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0686. Min Act: -0.0002

Data Index: 240026 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1257350 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0621. Min Act: -0.0001

Data Index: 407593 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1025078 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0638. Min Act: -0.0002

Data Index: 639469 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1448811 (Python Code)

Max Activating Token Index: 42

Text #9

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0608. Min Act: -0.0002

Data Index: 409955 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0609. Min Act: -0.0002

Data Index: 341805 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0635. Min Act: -0.0001

Data Index: 124633 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0602. Min Act: -0.0002

Data Index: 28442 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0564. Min Act: -0.0001

Data Index: 660960 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0569. Min Act: -0.0001

Data Index: 539690 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0613. Min Act: -0.0002

Data Index: 911816 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0579. Min Act: -0.0001

Data Index: 996279 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0636. Min Act: -0.0002

Data Index: 192712 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1332406 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0531. Min Act: -0.0001

Data Index: 402395 (C4 (Web Text))

Max Activating Token Index: 550