Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 959 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1414. Min Act: -0.0006

Data Index: 536674 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1400. Min Act: -0.0006

Data Index: 249333 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1217. Min Act: -0.0006

Data Index: 700333 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1141. Min Act: -0.0005

Data Index: 8829 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1060. Min Act: -0.0006

Data Index: 925636 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1019. Min Act: -0.0006

Data Index: 1000344 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1029. Min Act: -0.0006

Data Index: 462110 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1012. Min Act: -0.0006

Data Index: 1269423 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0974. Min Act: -0.0006

Data Index: 701400 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0991. Min Act: -0.0006

Data Index: 1343153 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0960. Min Act: -0.0006

Data Index: 1004936 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0976. Min Act: -0.0006

Data Index: 1016775 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0912. Min Act: -0.0006

Data Index: 674549 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0909. Min Act: -0.0006

Data Index: 359151 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0862. Min Act: -0.0006

Data Index: 105747 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0913. Min Act: -0.0006

Data Index: 1131158 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0869. Min Act: -0.0006

Data Index: 856301 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0864. Min Act: -0.0006

Data Index: 768902 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0845. Min Act: -0.0006

Data Index: 580942 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0831. Min Act: -0.0006

Data Index: 1299953 (C4 (Web Text))

Max Activating Token Index: 586