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

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

Neuron 4939 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.3083. Min Act: -0.0001

Data Index: 745139 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1800. Min Act: -0.0001

Data Index: 1186440 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1475. Min Act: -0.0001

Data Index: 19970 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1018. Min Act: -0.0001

Data Index: 790917 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0935. Min Act: -0.0001

Data Index: 1293626 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9267. Min Act: -0.0001

Data Index: 355802 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9842. Min Act: -0.0001

Data Index: 259174 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8989. Min Act: -0.0001

Data Index: 334814 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8889. Min Act: -0.0001

Data Index: 1288822 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8912. Min Act: -0.0001

Data Index: 121726 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9183. Min Act: -0.0000

Data Index: 392006 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8821. Min Act: -0.0001

Data Index: 230247 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9105. Min Act: -0.0001

Data Index: 1209343 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9151. Min Act: -0.0001

Data Index: 147216 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8581. Min Act: -0.0001

Data Index: 181124 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8542. Min Act: -0.0001

Data Index: 744720 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.7655. Min Act: -0.0001

Data Index: 1050547 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8488. Min Act: -0.0001

Data Index: 479166 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8582. Min Act: -0.0001

Data Index: 237069 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8581. Min Act: -0.0001

Data Index: 533944 (C4 (Web Text))

Max Activating Token Index: 869