Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1278 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1108. Min Act: -0.0004

Data Index: 1243173 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0003

Data Index: 513298 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1093. Min Act: -0.0004

Data Index: 1116789 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0994. Min Act: -0.0003

Data Index: 962003 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1113. Min Act: -0.0003

Data Index: 1151721 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1062. Min Act: -0.0003

Data Index: 62157 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0939. Min Act: -0.0004

Data Index: 450515 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1026. Min Act: -0.0003

Data Index: 1300959 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1002. Min Act: -0.0003

Data Index: 1186557 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1005. Min Act: -0.0003

Data Index: 1072880 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0937. Min Act: -0.0003

Data Index: 534119 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0904. Min Act: -0.0003

Data Index: 271809 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0989. Min Act: -0.0003

Data Index: 1242088 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0966. Min Act: -0.0004

Data Index: 1219943 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0960. Min Act: -0.0003

Data Index: 707029 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0981. Min Act: -0.0003

Data Index: 77277 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0940. Min Act: -0.0003

Data Index: 95883 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0945. Min Act: -0.0003

Data Index: 21462 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0938. Min Act: -0.0003

Data Index: 1260252 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0938. Min Act: -0.0003

Data Index: 1033497 (C4 (Web Text))

Max Activating Token Index: 678