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

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

Neuron 1406 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0602. Min Act: -0.0002

Data Index: 842603 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0617. Min Act: -0.0002

Data Index: 819593 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1183257 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0563. Min Act: -0.0002

Data Index: 362257 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0577. Min Act: -0.0002

Data Index: 820395 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0513. Min Act: -0.0002

Data Index: 573549 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0520. Min Act: -0.0002

Data Index: 200755 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0525. Min Act: -0.0002

Data Index: 662761 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0507. Min Act: -0.0002

Data Index: 813958 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1007257 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0472. Min Act: -0.0002

Data Index: 824561 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0486. Min Act: -0.0002

Data Index: 232793 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0478. Min Act: -0.0002

Data Index: 23568 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0458. Min Act: -0.0002

Data Index: 12147 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0442. Min Act: -0.0002

Data Index: 517368 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1161277 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1106540 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0433. Min Act: -0.0002

Data Index: 551913 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0433. Min Act: -0.0002

Data Index: 466511 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0467. Min Act: -0.0002

Data Index: 81562 (C4 (Web Text))

Max Activating Token Index: 451