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

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

Neuron 3053 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: 0.1384. Min Range: -0.1384

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1165586 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1200. Min Act: -0.0001

Data Index: 361014 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1224. Min Act: -0.0001

Data Index: 270191 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1203. Min Act: -0.0001

Data Index: 326956 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1087. Min Act: -0.0001

Data Index: 273872 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1081. Min Act: -0.0001

Data Index: 700848 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1175. Min Act: -0.0001

Data Index: 947704 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1098. Min Act: -0.0001

Data Index: 399441 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1141. Min Act: -0.0001

Data Index: 868519 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1290. Min Act: -0.0001

Data Index: 889087 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1105. Min Act: -0.0001

Data Index: 942191 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1139. Min Act: -0.0001

Data Index: 868540 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0861. Min Act: -0.0001

Data Index: 408062 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1060. Min Act: -0.0001

Data Index: 643095 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1148623 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1088288 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1096720 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0969. Min Act: -0.0001

Data Index: 990829 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0972. Min Act: -0.0001

Data Index: 903287 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0901. Min Act: -0.0001

Data Index: 340500 (C4 (Web Text))

Max Activating Token Index: 365