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

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

Neuron 2830 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1168. Min Act: -0.0001

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1072. Min Act: -0.0001

Data Index: 810844 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1079. Min Act: -0.0000

Data Index: 935535 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1036. Min Act: -0.0001

Data Index: 768790 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0947. Min Act: -0.0001

Data Index: 776851 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1337969 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1125461 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1109. Min Act: -0.0001

Data Index: 48123 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1046. Min Act: -0.0001

Data Index: 747765 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1078. Min Act: -0.0001

Data Index: 407941 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0938. Min Act: -0.0001

Data Index: 809645 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1029. Min Act: -0.0001

Data Index: 320200 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0989. Min Act: -0.0001

Data Index: 36450 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0974. Min Act: -0.0001

Data Index: 248335 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0934. Min Act: -0.0001

Data Index: 88623 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1015. Min Act: -0.0001

Data Index: 567886 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1155700 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0934. Min Act: -0.0001

Data Index: 984876 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0960. Min Act: -0.0001

Data Index: 401859 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0958. Min Act: -0.0001

Data Index: 139791 (C4 (Web Text))

Max Activating Token Index: 680