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

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

Neuron 4881 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.2202. Min Act: -0.0001

Data Index: 1090745 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.1539. Min Act: -0.0001

Data Index: 242801 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.1925. Min Act: -0.0001

Data Index: 763868 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0375. Min Act: -0.0001

Data Index: 1330207 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0390. Min Act: -0.0001

Data Index: 525271 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0523. Min Act: -0.0001

Data Index: 134526 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.2064. Min Act: -0.0001

Data Index: 265991 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0811. Min Act: -0.0001

Data Index: 1577789 (Python Code)

Max Activating Token Index: 940

Text #8

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0594. Min Act: -0.0001

Data Index: 845698 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 1.2202. Min Range: -1.2202

Max Act: 0.9943. Min Act: -0.0001

Data Index: 804132 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0965. Min Act: -0.0001

Data Index: 735142 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 1.2202. Min Range: -1.2202

Max Act: 0.9508. Min Act: -0.0001

Data Index: 683943 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0517. Min Act: -0.0001

Data Index: 979308 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0440. Min Act: -0.0001

Data Index: 791095 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0798. Min Act: -0.0001

Data Index: 522140 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.2202. Min Range: -1.2202

Max Act: 0.9533. Min Act: -0.0001

Data Index: 429126 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.2202. Min Range: -1.2202

Max Act: 0.9683. Min Act: -0.0001

Data Index: 241349 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0124. Min Act: -0.0001

Data Index: 953106 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.2202. Min Range: -1.2202

Max Act: 0.9800. Min Act: -0.0001

Data Index: 286167 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.2202. Min Range: -1.2202

Max Act: 1.0100. Min Act: -0.0001

Data Index: 1038332 (C4 (Web Text))

Max Activating Token Index: 53