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

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

Neuron 4267 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.2225. Min Act: -0.0000

Data Index: 185061 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1249190 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.1758. Min Act: -0.0000

Data Index: 562486 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.2053. Min Act: -0.0000

Data Index: 59835 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1253037 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0557. Min Act: -0.0000

Data Index: 45602 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0571. Min Act: -0.0000

Data Index: 749896 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0390. Min Act: -0.0000

Data Index: 224108 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9950. Min Act: -0.0000

Data Index: 250981 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1249831 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8937. Min Act: -0.0000

Data Index: 636001 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9582. Min Act: -0.0000

Data Index: 946263 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1186605 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0074. Min Act: -0.0000

Data Index: 687058 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9017. Min Act: -0.0000

Data Index: 951184 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9229. Min Act: -0.0000

Data Index: 484725 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1113594 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1179069 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9052. Min Act: -0.0000

Data Index: 97682 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9083. Min Act: -0.0000

Data Index: 387692 (C4 (Web Text))

Max Activating Token Index: 648