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

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

Neuron 3349 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0003

Data Index: 865740 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1356361 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0547. Min Act: -0.0003

Data Index: 487306 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0534. Min Act: -0.0003

Data Index: 632520 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0518. Min Act: -0.0003

Data Index: 776155 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0508. Min Act: -0.0003

Data Index: 549993 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0514. Min Act: -0.0003

Data Index: 13945 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0514. Min Act: -0.0003

Data Index: 668466 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0513. Min Act: -0.0003

Data Index: 371662 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0507. Min Act: -0.0002

Data Index: 646723 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0502. Min Act: -0.0003

Data Index: 233461 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0510. Min Act: -0.0002

Data Index: 715750 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0500. Min Act: -0.0003

Data Index: 669022 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0498. Min Act: -0.0002

Data Index: 229338 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0497. Min Act: -0.0003

Data Index: 767666 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0507. Min Act: -0.0003

Data Index: 986462 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0496. Min Act: -0.0003

Data Index: 984900 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0492. Min Act: -0.0003

Data Index: 897985 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1050432 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0500. Min Act: -0.0003

Data Index: 455651 (C4 (Web Text))

Max Activating Token Index: 411