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

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

Neuron 5168 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: 4.1651. Min Range: -4.1651

Max Act: 4.1651. Min Act: -0.0000

Data Index: 1555758 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 4.1651. Min Range: -4.1651

Max Act: 4.0283. Min Act: -0.0000

Data Index: 1536356 (Python Code)

Max Activating Token Index: 436

Text #2

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.4933. Min Act: -0.0000

Data Index: 1520618 (Python Code)

Max Activating Token Index: 684

Text #3

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.5353. Min Act: -0.0000

Data Index: 1652941 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.1566. Min Act: -0.0000

Data Index: 1470113 (Python Code)

Max Activating Token Index: 264

Text #5

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.1659. Min Act: -0.0000

Data Index: 1368608 (Python Code)

Max Activating Token Index: 916

Text #6

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.2048. Min Act: -0.0000

Data Index: 1477922 (Python Code)

Max Activating Token Index: 454

Text #7

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.9196. Min Act: -0.0000

Data Index: 1381742 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 4.1651. Min Range: -4.1651

Max Act: 3.0511. Min Act: -0.0000

Data Index: 1440255 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.8019. Min Act: -0.0000

Data Index: 1480480 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.6117. Min Act: -0.0000

Data Index: 1625921 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.4008. Min Act: -0.0000

Data Index: 1478981 (Python Code)

Max Activating Token Index: 131

Text #12

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.6348. Min Act: -0.0000

Data Index: 1583260 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.6242. Min Act: -0.0000

Data Index: 1377950 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.4612. Min Act: -0.0000

Data Index: 1400243 (Python Code)

Max Activating Token Index: 785

Text #15

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.5764. Min Act: -0.0000

Data Index: 1640454 (Python Code)

Max Activating Token Index: 212

Text #16

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.5421. Min Act: -0.0000

Data Index: 1491219 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.6826. Min Act: -0.0000

Data Index: 1620747 (Python Code)

Max Activating Token Index: 915

Text #18

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.2741. Min Act: -0.0000

Data Index: 1602511 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 4.1651. Min Range: -4.1651

Max Act: 2.4858. Min Act: -0.0000

Data Index: 1544782 (Python Code)

Max Activating Token Index: 593