Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2256 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1045835 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1114950 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1022023 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1416. Min Act: -0.0000

Data Index: 187684 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1191286 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1327145 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1312. Min Act: -0.0000

Data Index: 957136 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1240. Min Act: -0.0000

Data Index: 204251 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1260. Min Act: -0.0000

Data Index: 540847 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1136. Min Act: -0.0000

Data Index: 228738 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1145. Min Act: -0.0000

Data Index: 833085 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1126. Min Act: -0.0000

Data Index: 137386 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1084. Min Act: -0.0000

Data Index: 572113 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1076. Min Act: -0.0000

Data Index: 701954 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1094. Min Act: -0.0000

Data Index: 88927 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0994. Min Act: -0.0000

Data Index: 613774 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1044. Min Act: -0.0000

Data Index: 416578 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1037. Min Act: -0.0000

Data Index: 549736 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1022. Min Act: -0.0000

Data Index: 470370 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1029. Min Act: -0.0000

Data Index: 977734 (C4 (Web Text))

Max Activating Token Index: 66