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

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

Neuron 3154 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3778. Min Act: -0.0001

Data Index: 1603544 (Python Code)

Max Activating Token Index: 937

Text #1

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3543. Min Act: -0.0001

Data Index: 1621944 (Python Code)

Max Activating Token Index: 235

Text #2

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3606. Min Act: -0.0001

Data Index: 1624023 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3806. Min Act: -0.0000

Data Index: 802054 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3443. Min Act: -0.0001

Data Index: 1377056 (Python Code)

Max Activating Token Index: 541

Text #5

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3376. Min Act: -0.0001

Data Index: 1468592 (Python Code)

Max Activating Token Index: 996

Text #6

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3683. Min Act: -0.0001

Data Index: 1573929 (Python Code)

Max Activating Token Index: 495

Text #7

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2790. Min Act: -0.0001

Data Index: 1572899 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3359. Min Act: -0.0001

Data Index: 1420573 (Python Code)

Max Activating Token Index: 600

Text #9

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1582137 (Python Code)

Max Activating Token Index: 969

Text #10

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3565. Min Act: -0.0001

Data Index: 1602391 (Python Code)

Max Activating Token Index: 859

Text #11

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1500698 (Python Code)

Max Activating Token Index: 686

Text #12

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3608. Min Act: -0.0001

Data Index: 1620724 (Python Code)

Max Activating Token Index: 644

Text #13

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3516. Min Act: -0.0001

Data Index: 1369036 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3124. Min Act: -0.0001

Data Index: 1470880 (Python Code)

Max Activating Token Index: 951

Text #15

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1443019 (Python Code)

Max Activating Token Index: 599

Text #16

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3094. Min Act: -0.0001

Data Index: 1625512 (Python Code)

Max Activating Token Index: 675

Text #17

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3013. Min Act: -0.0001

Data Index: 1479922 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2891. Min Act: -0.0001

Data Index: 1438980 (Python Code)

Max Activating Token Index: 633

Text #19

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1612557 (Python Code)

Max Activating Token Index: 601