Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 902 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1380639 (Python Code)

Max Activating Token Index: 263

Text #1

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0504. Min Act: -0.0003

Data Index: 216003 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0483. Min Act: -0.0003

Data Index: 506709 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1158433 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1646783 (Python Code)

Max Activating Token Index: 394

Text #5

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0464. Min Act: -0.0003

Data Index: 785354 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0442. Min Act: -0.0003

Data Index: 84646 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1128925 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1559521 (Python Code)

Max Activating Token Index: 298

Text #9

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0448. Min Act: -0.0004

Data Index: 1597868 (Python Code)

Max Activating Token Index: 517

Text #10

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0446. Min Act: -0.0003

Data Index: 41394 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0444. Min Act: -0.0003

Data Index: 472323 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0443. Min Act: -0.0003

Data Index: 384525 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1440944 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0444. Min Act: -0.0003

Data Index: 433910 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1389639 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0437. Min Act: -0.0003

Data Index: 554860 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0442. Min Act: -0.0004

Data Index: 682813 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0434. Min Act: -0.0003

Data Index: 437813 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0431. Min Act: -0.0003

Data Index: 248710 (C4 (Web Text))

Max Activating Token Index: 650