Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2935 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.2465. Min Act: -0.0000

Data Index: 80056 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.2637. Min Act: -0.0000

Data Index: 1100415 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1191157 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1351561 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.6203. Min Act: -0.0000

Data Index: 956141 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.6414. Min Act: -0.0000

Data Index: 635801 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.6013. Min Act: -0.0000

Data Index: 612487 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1449359 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1524514 (Python Code)

Max Activating Token Index: 758

Text #9

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1489537 (Python Code)

Max Activating Token Index: 915

Text #10

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.5497. Min Act: -0.0000

Data Index: 915924 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1628247 (Python Code)

Max Activating Token Index: 756

Text #12

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1016156 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1182794 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.4605. Min Act: -0.0000

Data Index: 958805 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1511293 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1244141 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1367896 (Python Code)

Max Activating Token Index: 472

Text #18

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.4820. Min Act: -0.0000

Data Index: 257393 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1591291 (Python Code)

Max Activating Token Index: 457