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

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

Neuron 798 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1700. Min Act: -0.0000

Data Index: 819907 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1738. Min Act: -0.0000

Data Index: 946628 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1198. Min Act: -0.0000

Data Index: 302138 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1191. Min Act: -0.0000

Data Index: 208452 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1098. Min Act: -0.0000

Data Index: 859180 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1087. Min Act: -0.0000

Data Index: 81481 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1185. Min Act: -0.0000

Data Index: 951056 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1277785 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1327791 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1019. Min Act: -0.0000

Data Index: 652071 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1046. Min Act: -0.0000

Data Index: 598051 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1113. Min Act: -0.0000

Data Index: 782778 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0996. Min Act: -0.0000

Data Index: 352820 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1027. Min Act: -0.0000

Data Index: 618354 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0908. Min Act: -0.0000

Data Index: 716036 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1203886 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0922. Min Act: -0.0000

Data Index: 94475 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1157851 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0831. Min Act: -0.0000

Data Index: 535140 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0898. Min Act: -0.0000

Data Index: 397091 (C4 (Web Text))

Max Activating Token Index: 763