Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1080 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6976. Min Act: -0.0000

Data Index: 991755 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6707. Min Act: -0.0000

Data Index: 370986 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5296. Min Act: -0.0000

Data Index: 816978 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5023. Min Act: -0.0000

Data Index: 279647 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.4254. Min Act: -0.0000

Data Index: 807353 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1347143 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3909. Min Act: -0.0000

Data Index: 786364 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.4066. Min Act: -0.0000

Data Index: 235730 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3647. Min Act: -0.0000

Data Index: 990992 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3816. Min Act: -0.0000

Data Index: 257354 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3774. Min Act: -0.0000

Data Index: 367545 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3489. Min Act: -0.0000

Data Index: 928466 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3660. Min Act: -0.0000

Data Index: 661497 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3553. Min Act: -0.0000

Data Index: 503050 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3679. Min Act: -0.0000

Data Index: 619632 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1144836 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3506. Min Act: -0.0000

Data Index: 540803 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3331. Min Act: -0.0000

Data Index: 935000 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3591. Min Act: -0.0000

Data Index: 591472 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.3475. Min Act: -0.0000

Data Index: 519999 (C4 (Web Text))

Max Activating Token Index: 713