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

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

Neuron 2871 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1968. Min Act: -0.0002

Data Index: 1321394 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1825. Min Act: -0.0002

Data Index: 91553 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1794. Min Act: -0.0002

Data Index: 1484409 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1779. Min Act: -0.0002

Data Index: 668424 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1774. Min Act: -0.0002

Data Index: 111309 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1760. Min Act: -0.0002

Data Index: 138030 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1674. Min Act: -0.0002

Data Index: 464681 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1712. Min Act: -0.0002

Data Index: 255691 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1639. Min Act: -0.0002

Data Index: 117781 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1712. Min Act: -0.0002

Data Index: 1585828 (Python Code)

Max Activating Token Index: 77

Text #10

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1645. Min Act: -0.0002

Data Index: 454850 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1648. Min Act: -0.0002

Data Index: 346196 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1668. Min Act: -0.0002

Data Index: 230628 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1687. Min Act: -0.0002

Data Index: 1332767 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1642. Min Act: -0.0002

Data Index: 1389757 (Python Code)

Max Activating Token Index: 136

Text #15

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1655. Min Act: -0.0002

Data Index: 221877 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1641. Min Act: -0.0002

Data Index: 798498 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1637. Min Act: -0.0002

Data Index: 1504907 (Python Code)

Max Activating Token Index: 612

Text #18

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1657. Min Act: -0.0002

Data Index: 331936 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1638. Min Act: -0.0002

Data Index: 1048627 (C4 (Web Text))

Max Activating Token Index: 547