Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2591 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1465247 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3807. Min Act: -0.0000

Data Index: 866901 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1433448 (Python Code)

Max Activating Token Index: 1004

Text #3

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3962. Min Act: -0.0000

Data Index: 625811 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1241986 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3709. Min Act: -0.0000

Data Index: 43014 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3721. Min Act: -0.0000

Data Index: 399621 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3628. Min Act: -0.0000

Data Index: 337249 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3617. Min Act: -0.0000

Data Index: 681383 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1062915 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3708. Min Act: -0.0000

Data Index: 122494 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1566557 (Python Code)

Max Activating Token Index: 247

Text #12

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3598. Min Act: -0.0000

Data Index: 330022 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1440727 (Python Code)

Max Activating Token Index: 649

Text #14

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1202038 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3649. Min Act: -0.0000

Data Index: 683788 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3532. Min Act: -0.0000

Data Index: 89376 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3665. Min Act: -0.0000

Data Index: 395019 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3287. Min Act: -0.0000

Data Index: 384832 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1452611 (Python Code)

Max Activating Token Index: 679