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

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

Neuron 886 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7957. Min Act: -0.0000

Data Index: 499497 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7989. Min Act: -0.0000

Data Index: 954346 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7625. Min Act: -0.0000

Data Index: 102065 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7593. Min Act: -0.0000

Data Index: 370179 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7321. Min Act: -0.0000

Data Index: 534337 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7400. Min Act: -0.0000

Data Index: 947555 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6865. Min Act: -0.0000

Data Index: 527203 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6539. Min Act: -0.0000

Data Index: 269855 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6076. Min Act: -0.0000

Data Index: 55156 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6481. Min Act: -0.0000

Data Index: 26235 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6037. Min Act: -0.0000

Data Index: 594772 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6324. Min Act: -0.0000

Data Index: 80884 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6066. Min Act: -0.0000

Data Index: 765898 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6086. Min Act: -0.0000

Data Index: 791343 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1074459 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6651. Min Act: -0.0000

Data Index: 615919 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6385. Min Act: -0.0000

Data Index: 861587 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1318775 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6040. Min Act: -0.0000

Data Index: 940853 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6183. Min Act: -0.0000

Data Index: 376680 (C4 (Web Text))

Max Activating Token Index: 215