Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 566 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0606. Min Act: -0.0002

Data Index: 805011 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1231197 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0521. Min Act: -0.0002

Data Index: 488551 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1196081 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0490. Min Act: -0.0002

Data Index: 990774 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0457. Min Act: -0.0002

Data Index: 569434 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0488. Min Act: -0.0002

Data Index: 683944 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0490. Min Act: -0.0002

Data Index: 909267 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0474. Min Act: -0.0002

Data Index: 821773 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0487. Min Act: -0.0002

Data Index: 935929 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0481. Min Act: -0.0002

Data Index: 845286 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0454. Min Act: -0.0002

Data Index: 124485 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0465. Min Act: -0.0001

Data Index: 494115 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1252911 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0476. Min Act: -0.0002

Data Index: 86600 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1270614 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0446. Min Act: -0.0002

Data Index: 420562 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0444. Min Act: -0.0002

Data Index: 733019 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1315746 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0452. Min Act: -0.0002

Data Index: 172417 (C4 (Web Text))

Max Activating Token Index: 587