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

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

Neuron 5021 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1344. Min Act: -0.0000

Data Index: 130483 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1215. Min Act: -0.0000

Data Index: 291493 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1213. Min Act: -0.0000

Data Index: 16450 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1143. Min Act: -0.0000

Data Index: 959495 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1030. Min Act: -0.0000

Data Index: 903538 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1054. Min Act: -0.0000

Data Index: 550548 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1068. Min Act: -0.0000

Data Index: 224068 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0992. Min Act: -0.0000

Data Index: 443145 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1319547 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0965. Min Act: -0.0000

Data Index: 34322 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0979. Min Act: -0.0000

Data Index: 817541 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1269040 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1318278 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1317312 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0912. Min Act: -0.0000

Data Index: 484483 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0951. Min Act: -0.0000

Data Index: 121678 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0923. Min Act: -0.0000

Data Index: 861113 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1105569 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1145143 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0910. Min Act: -0.0000

Data Index: 534209 (C4 (Web Text))

Max Activating Token Index: 936