Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1625 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0001

Data Index: 565604 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0918. Min Act: -0.0001

Data Index: 322529 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0786. Min Act: -0.0001

Data Index: 212601 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1263660 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0643. Min Act: -0.0001

Data Index: 207026 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0680. Min Act: -0.0001

Data Index: 211202 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0664. Min Act: -0.0001

Data Index: 764972 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1113680 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0592. Min Act: -0.0001

Data Index: 74456 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0581. Min Act: -0.0001

Data Index: 990066 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0571. Min Act: -0.0001

Data Index: 166011 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0580. Min Act: -0.0002

Data Index: 949398 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0598. Min Act: -0.0001

Data Index: 405607 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0551. Min Act: -0.0001

Data Index: 540351 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1265119 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0593. Min Act: -0.0001

Data Index: 812532 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0545. Min Act: -0.0001

Data Index: 284822 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1354412 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0539. Min Act: -0.0002

Data Index: 528600 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0508. Min Act: -0.0001

Data Index: 622128 (C4 (Web Text))

Max Activating Token Index: 132