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

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

Neuron 1654 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0563. Min Act: -0.0006

Data Index: 325677 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0548. Min Act: -0.0006

Data Index: 386031 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0525. Min Act: -0.0006

Data Index: 1614182 (Python Code)

Max Activating Token Index: 505

Text #3

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0524. Min Act: -0.0006

Data Index: 503389 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0521. Min Act: -0.0006

Data Index: 376752 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0518. Min Act: -0.0006

Data Index: 478183 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0522. Min Act: -0.0006

Data Index: 629829 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0503. Min Act: -0.0006

Data Index: 1170228 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0504. Min Act: -0.0006

Data Index: 715556 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0512. Min Act: -0.0006

Data Index: 688003 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0499. Min Act: -0.0006

Data Index: 624318 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0494. Min Act: -0.0006

Data Index: 1299512 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0491. Min Act: -0.0006

Data Index: 1622020 (Python Code)

Max Activating Token Index: 981

Text #13

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0479. Min Act: -0.0006

Data Index: 1156983 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0476. Min Act: -0.0006

Data Index: 1485732 (Python Code)

Max Activating Token Index: 859

Text #15

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0487. Min Act: -0.0006

Data Index: 1051746 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0489. Min Act: -0.0006

Data Index: 787369 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1175918 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0459. Min Act: -0.0006

Data Index: 1209823 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0467. Min Act: -0.0006

Data Index: 950240 (C4 (Web Text))

Max Activating Token Index: 506