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

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

Neuron 5071 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1369. Min Act: -0.0002

Data Index: 840135 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1209. Min Act: -0.0002

Data Index: 1007563 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1158. Min Act: -0.0002

Data Index: 596496 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1132. Min Act: -0.0002

Data Index: 553580 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1283. Min Act: -0.0002

Data Index: 1325966 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1132. Min Act: -0.0002

Data Index: 919401 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1111. Min Act: -0.0002

Data Index: 461904 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1040. Min Act: -0.0002

Data Index: 355666 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1017. Min Act: -0.0002

Data Index: 286642 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1199862 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1239. Min Act: -0.0002

Data Index: 580109 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0983. Min Act: -0.0002

Data Index: 19185 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1153639 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0971. Min Act: -0.0002

Data Index: 423008 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0964. Min Act: -0.0002

Data Index: 16380 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1055621 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0970. Min Act: -0.0002

Data Index: 337652 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1126580 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0929. Min Act: -0.0002

Data Index: 585002 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.0956. Min Act: -0.0002

Data Index: 264363 (C4 (Web Text))

Max Activating Token Index: 1005