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

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

Neuron 5562 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.3703. Min Act: -0.0000

Data Index: 476771 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.3651. Min Act: -0.0000

Data Index: 461217 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1023802 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1372274 (Python Code)

Max Activating Token Index: 653

Text #4

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1321853 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1653432 (Python Code)

Max Activating Token Index: 401

Text #6

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.3171. Min Act: -0.0000

Data Index: 921970 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.3025. Min Act: -0.0000

Data Index: 694994 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1412540 (Python Code)

Max Activating Token Index: 514

Text #9

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1593207 (Python Code)

Max Activating Token Index: 208

Text #10

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1363773 (Python Code)

Max Activating Token Index: 384

Text #11

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2623. Min Act: -0.0000

Data Index: 116459 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1350390 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2599. Min Act: -0.0000

Data Index: 222857 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2585. Min Act: -0.0000

Data Index: 455590 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2576. Min Act: -0.0000

Data Index: 954450 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1528025 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2548. Min Act: -0.0000

Data Index: 191700 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2459. Min Act: -0.0000

Data Index: 739627 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.3703. Min Range: -0.3703

Max Act: 0.2550. Min Act: -0.0000

Data Index: 392917 (C4 (Web Text))

Max Activating Token Index: 306