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

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

Neuron 2355 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1138904 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7572. Min Act: -0.0000

Data Index: 211113 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1118193 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7429. Min Act: -0.0000

Data Index: 785478 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7485. Min Act: -0.0000

Data Index: 255619 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1060981 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7441. Min Act: -0.0000

Data Index: 743128 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7175. Min Act: -0.0000

Data Index: 568317 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7821. Min Act: -0.0000

Data Index: 10566 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1237874 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7015. Min Act: -0.0000

Data Index: 968766 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7008. Min Act: -0.0000

Data Index: 413117 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1155775 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1016813 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6608. Min Act: -0.0000

Data Index: 799128 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5616. Min Act: -0.0000

Data Index: 848780 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5495. Min Act: -0.0000

Data Index: 593425 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1029541 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1316208 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5117. Min Act: -0.0000

Data Index: 555688 (C4 (Web Text))

Max Activating Token Index: 534