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

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

Neuron 1323 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: 0.4789. Min Range: -0.4789

Max Act: 0.4789. Min Act: -0.0002

Data Index: 486606 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4548. Min Act: -0.0002

Data Index: 380649 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4366. Min Act: -0.0002

Data Index: 281295 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4119. Min Act: -0.0002

Data Index: 1556622 (Python Code)

Max Activating Token Index: 106

Text #4

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4120. Min Act: -0.0002

Data Index: 1593900 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4017. Min Act: -0.0002

Data Index: 1637370 (Python Code)

Max Activating Token Index: 177

Text #6

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3796. Min Act: -0.0002

Data Index: 1609695 (Python Code)

Max Activating Token Index: 494

Text #7

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3740. Min Act: -0.0002

Data Index: 1377892 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3694. Min Act: -0.0002

Data Index: 480164 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3760. Min Act: -0.0002

Data Index: 15674 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3696. Min Act: -0.0002

Data Index: 163149 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3612. Min Act: -0.0002

Data Index: 357717 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3700. Min Act: -0.0002

Data Index: 902808 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3657. Min Act: -0.0002

Data Index: 1011627 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3650. Min Act: -0.0002

Data Index: 1475906 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3598. Min Act: -0.0002

Data Index: 1650699 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3630. Min Act: -0.0002

Data Index: 1579637 (Python Code)

Max Activating Token Index: 20

Text #17

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3662. Min Act: -0.0002

Data Index: 1495508 (Python Code)

Max Activating Token Index: 434

Text #18

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3496. Min Act: -0.0002

Data Index: 1446765 (Python Code)

Max Activating Token Index: 126

Text #19

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3593. Min Act: -0.0002

Data Index: 1421862 (Python Code)

Max Activating Token Index: 15