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

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

Neuron 4058 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2540. Min Act: -0.0001

Data Index: 1019092 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1875. Min Act: -0.0001

Data Index: 1275998 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1802. Min Act: -0.0001

Data Index: 361483 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1809. Min Act: -0.0001

Data Index: 222197 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1621. Min Act: -0.0001

Data Index: 821558 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1576. Min Act: -0.0001

Data Index: 401520 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1630. Min Act: -0.0001

Data Index: 841148 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1609. Min Act: -0.0001

Data Index: 937141 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1622. Min Act: -0.0001

Data Index: 106641 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1656. Min Act: -0.0001

Data Index: 106373 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1534. Min Act: -0.0001

Data Index: 336045 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1512. Min Act: -0.0001

Data Index: 207991 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1018599 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1503. Min Act: -0.0001

Data Index: 68520 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1333. Min Act: -0.0001

Data Index: 348715 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1493. Min Act: -0.0001

Data Index: 59418 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1493. Min Act: -0.0001

Data Index: 199467 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1527. Min Act: -0.0001

Data Index: 581013 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1382. Min Act: -0.0001

Data Index: 203701 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1438. Min Act: -0.0001

Data Index: 581678 (C4 (Web Text))

Max Activating Token Index: 523