Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2998 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1407. Min Act: -0.0004

Data Index: 772194 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1159. Min Act: -0.0004

Data Index: 547993 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1077. Min Act: -0.0004

Data Index: 1027701 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0595. Min Act: -0.0004

Data Index: 1068742 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0932. Min Act: -0.0004

Data Index: 873925 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1126. Min Act: -0.0004

Data Index: 701687 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0850. Min Act: -0.0004

Data Index: 545391 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0953. Min Act: -0.0004

Data Index: 890858 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0985. Min Act: -0.0004

Data Index: 1262262 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0997. Min Act: -0.0004

Data Index: 1346442 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1020. Min Act: -0.0004

Data Index: 26382 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1182. Min Act: -0.0004

Data Index: 80844 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0857. Min Act: -0.0004

Data Index: 1069909 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1043. Min Act: -0.0004

Data Index: 867906 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0973. Min Act: -0.0004

Data Index: 768444 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1035. Min Act: -0.0004

Data Index: 155073 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0921. Min Act: -0.0004

Data Index: 790869 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1029. Min Act: -0.0004

Data Index: 879581 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1033. Min Act: -0.0004

Data Index: 690393 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1037. Min Act: -0.0004

Data Index: 1325477 (C4 (Web Text))

Max Activating Token Index: 237