Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 172 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.8298. Min Act: -0.0001

Data Index: 353416 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.5083. Min Act: -0.0001

Data Index: 1090103 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.3924. Min Act: -0.0001

Data Index: 98566 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.3430. Min Act: -0.0001

Data Index: 44371 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.1832. Min Act: -0.0001

Data Index: 1589059 (Python Code)

Max Activating Token Index: 200

Text #5

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.1749. Min Act: -0.0001

Data Index: 477824 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.1738. Min Act: -0.0001

Data Index: 210418 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.1603. Min Act: -0.0001

Data Index: 569088 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.0683. Min Act: -0.0001

Data Index: 974726 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.1017. Min Act: -0.0001

Data Index: 822476 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.0578. Min Act: -0.0001

Data Index: 1626639 (Python Code)

Max Activating Token Index: 936

Text #11

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.0805. Min Act: -0.0001

Data Index: 1378220 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.0875. Min Act: -0.0001

Data Index: 1179577 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.1244. Min Act: -0.0001

Data Index: 182846 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.0862. Min Act: -0.0001

Data Index: 986831 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.1535. Min Act: -0.0001

Data Index: 1159603 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.0852. Min Act: -0.0001

Data Index: 765312 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.0992. Min Act: -0.0001

Data Index: 262236 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.0188. Min Act: -0.0001

Data Index: 1545988 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 1.8298. Min Range: -1.8298

Max Act: 1.0489. Min Act: -0.0001

Data Index: 239793 (C4 (Web Text))

Max Activating Token Index: 882