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

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

Neuron 4740 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: 0.2486. Min Range: -0.2486

Max Act: 0.2486. Min Act: -0.0001

Data Index: 290553 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2185. Min Act: -0.0001

Data Index: 1248404 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1771. Min Act: -0.0001

Data Index: 827829 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2247. Min Act: -0.0001

Data Index: 98521 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2427. Min Act: -0.0001

Data Index: 538441 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2139. Min Act: -0.0001

Data Index: 960568 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2221. Min Act: -0.0001

Data Index: 887706 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1986. Min Act: -0.0001

Data Index: 840367 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1999. Min Act: -0.0001

Data Index: 1207650 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2101. Min Act: -0.0001

Data Index: 896137 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1983. Min Act: -0.0001

Data Index: 682811 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1957. Min Act: -0.0001

Data Index: 705324 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1813. Min Act: -0.0001

Data Index: 1268271 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2029. Min Act: -0.0001

Data Index: 683072 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1194921 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2065. Min Act: -0.0001

Data Index: 629136 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2072. Min Act: -0.0001

Data Index: 863394 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2054. Min Act: -0.0001

Data Index: 66105 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1248779 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1975. Min Act: -0.0001

Data Index: 109876 (C4 (Web Text))

Max Activating Token Index: 515