Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2398 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1080. Min Act: -0.0000

Data Index: 897781 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1085. Min Act: -0.0000

Data Index: 527514 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1157. Min Act: -0.0001

Data Index: 249156 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1080. Min Act: 0.0000

Data Index: 363770 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1054. Min Act: -0.0000

Data Index: 948805 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1018613 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0919. Min Act: -0.0000

Data Index: 268196 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1637290 (Python Code)

Max Activating Token Index: 736

Text #8

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1494761 (Python Code)

Max Activating Token Index: 728

Text #9

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0863. Min Act: -0.0000

Data Index: 226977 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0991. Min Act: 0.0000

Data Index: 239553 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0874. Min Act: -0.0001

Data Index: 216040 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1123532 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0976. Min Act: -0.0000

Data Index: 889973 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0869. Min Act: -0.0000

Data Index: 829032 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0875. Min Act: 0.0000

Data Index: 376302 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0869. Min Act: -0.0001

Data Index: 491526 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0866. Min Act: 0.0000

Data Index: 158142 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1630254 (Python Code)

Max Activating Token Index: 700

Text #19

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0893. Min Act: 0.0000

Data Index: 786685 (C4 (Web Text))

Max Activating Token Index: 404