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

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

Neuron 3327 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: 1.9765. Min Range: -1.9765

Max Act: 1.9765. Min Act: -0.0002

Data Index: 311817 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.9468. Min Act: -0.0002

Data Index: 434267 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.9193. Min Act: -0.0002

Data Index: 876504 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.7678. Min Act: -0.0002

Data Index: 1160712 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.7623. Min Act: -0.0002

Data Index: 553779 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.6924. Min Act: -0.0002

Data Index: 662614 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.6006. Min Act: -0.0002

Data Index: 817915 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.5890. Min Act: -0.0002

Data Index: 679661 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.4758. Min Act: -0.0003

Data Index: 299201 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.4805. Min Act: -0.0002

Data Index: 825904 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.5046. Min Act: -0.0002

Data Index: 639432 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.4903. Min Act: -0.0002

Data Index: 802248 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.4518. Min Act: -0.0002

Data Index: 873235 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.4134. Min Act: -0.0002

Data Index: 813810 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.4055. Min Act: -0.0002

Data Index: 370829 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.4275. Min Act: -0.0002

Data Index: 823618 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.3792. Min Act: -0.0002

Data Index: 1184941 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.3715. Min Act: -0.0002

Data Index: 307508 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.3781. Min Act: -0.0002

Data Index: 331081 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.9765. Min Range: -1.9765

Max Act: 1.3323. Min Act: -0.0002

Data Index: 504667 (C4 (Web Text))

Max Activating Token Index: 677