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

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

Neuron 2551 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3194. Min Range: -2.3194

Max Act: 2.3194. Min Act: -0.0000

Data Index: 380919 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.6099. Min Act: -0.0000

Data Index: 1192947 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.5526. Min Act: -0.0000

Data Index: 832015 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.4270. Min Act: -0.0000

Data Index: 683871 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.3134. Min Act: -0.0000

Data Index: 974596 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.2860. Min Act: -0.0000

Data Index: 151244 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.2607. Min Act: 0.0001

Data Index: 877858 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.2670. Min Act: -0.0000

Data Index: 756132 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.2513. Min Act: -0.0000

Data Index: 9747 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.2130. Min Act: 0.0001

Data Index: 393420 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.1193. Min Act: -0.0000

Data Index: 569957 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.1041. Min Act: -0.0000

Data Index: 242719 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.1592. Min Act: -0.0000

Data Index: 1191851 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.1414. Min Act: -0.0000

Data Index: 618790 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.1594. Min Act: -0.0000

Data Index: 674291 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1161909 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.1595. Min Act: -0.0000

Data Index: 1214914 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1320656 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 2.3194. Min Range: -2.3194

Max Act: 1.0928. Min Act: -0.0000

Data Index: 713801 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 2.3194. Min Range: -2.3194

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1035221 (C4 (Web Text))

Max Activating Token Index: 927