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

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

Neuron 3816 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: 0.0880. Min Range: -0.0880

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1476205 (Python Code)

Max Activating Token Index: 243

Text #1

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1643384 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0833. Min Act: -0.0002

Data Index: 481847 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1547821 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1391593 (Python Code)

Max Activating Token Index: 93

Text #5

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1178264 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1414136 (Python Code)

Max Activating Token Index: 931

Text #7

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1409453 (Python Code)

Max Activating Token Index: 998

Text #8

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1339678 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1473303 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1011779 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0789. Min Act: -0.0002

Data Index: 100332 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1585944 (Python Code)

Max Activating Token Index: 840

Text #13

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0749. Min Act: -0.0002

Data Index: 973700 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0758. Min Act: -0.0002

Data Index: 490035 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1441356 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1431312 (Python Code)

Max Activating Token Index: 451

Text #17

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0752. Min Act: -0.0002

Data Index: 757811 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1464716 (Python Code)

Max Activating Token Index: 364

Text #19

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0754. Min Act: -0.0002

Data Index: 607928 (C4 (Web Text))

Max Activating Token Index: 127