Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1458 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.3720. Min Act: -0.0001

Data Index: 1096396 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2543. Min Act: -0.0001

Data Index: 1040809 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.3107. Min Act: -0.0001

Data Index: 610608 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.3276. Min Act: -0.0001

Data Index: 427004 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.3371. Min Act: -0.0001

Data Index: 332951 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2726. Min Act: -0.0001

Data Index: 112702 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2961. Min Act: -0.0001

Data Index: 1118319 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1106389 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.3137. Min Act: -0.0001

Data Index: 801209 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2669. Min Act: -0.0001

Data Index: 431265 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.3052. Min Act: -0.0001

Data Index: 1188009 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.3119. Min Act: -0.0001

Data Index: 429841 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2626. Min Act: -0.0001

Data Index: 841439 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1294333 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1206908 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2649. Min Act: -0.0001

Data Index: 1245819 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.3013. Min Act: -0.0001

Data Index: 612155 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2605. Min Act: -0.0001

Data Index: 60783 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2715. Min Act: -0.0001

Data Index: 870711 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.3720. Min Range: -0.3720

Max Act: 0.2705. Min Act: -0.0001

Data Index: 1190457 (C4 (Web Text))

Max Activating Token Index: 23