Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1000 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.4393. Min Act: -0.0001

Data Index: 596156 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.4276. Min Act: -0.0001

Data Index: 54946 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.4074. Min Act: -0.0001

Data Index: 1166516 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3918. Min Act: -0.0001

Data Index: 709916 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3912. Min Act: -0.0001

Data Index: 475875 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3662. Min Act: -0.0001

Data Index: 549743 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3840. Min Act: -0.0001

Data Index: 450091 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3816. Min Act: -0.0001

Data Index: 745784 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3802. Min Act: -0.0001

Data Index: 560096 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3574. Min Act: -0.0001

Data Index: 1276973 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3555. Min Act: -0.0001

Data Index: 1107514 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3501. Min Act: -0.0001

Data Index: 36737 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3418. Min Act: -0.0001

Data Index: 382797 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3497. Min Act: -0.0001

Data Index: 859928 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3317. Min Act: -0.0001

Data Index: 479471 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3582. Min Act: -0.0001

Data Index: 220279 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3417. Min Act: -0.0001

Data Index: 744107 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3313. Min Act: -0.0001

Data Index: 1245502 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3325. Min Act: -0.0001

Data Index: 774103 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.4393. Min Range: -0.4393

Max Act: 0.3420. Min Act: -0.0001

Data Index: 512094 (C4 (Web Text))

Max Activating Token Index: 620