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

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

Neuron 1925 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: 0.1112. Min Range: -0.1112

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1517235 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1042. Min Act: -0.0002

Data Index: 667969 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0951. Min Act: -0.0002

Data Index: 458686 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0937. Min Act: -0.0002

Data Index: 43608 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0923. Min Act: -0.0002

Data Index: 77184 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0924. Min Act: -0.0002

Data Index: 587889 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1337649 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1589382 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0865. Min Act: -0.0002

Data Index: 203949 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0862. Min Act: -0.0002

Data Index: 126301 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0829. Min Act: -0.0002

Data Index: 929934 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0846. Min Act: -0.0002

Data Index: 61873 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1598904 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0814. Min Act: -0.0002

Data Index: 237439 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0813. Min Act: -0.0002

Data Index: 347884 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0814. Min Act: -0.0002

Data Index: 282280 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0818. Min Act: -0.0002

Data Index: 544441 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0802. Min Act: -0.0002

Data Index: 723400 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0814. Min Act: -0.0002

Data Index: 571881 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1533988 (Python Code)

Max Activating Token Index: 2