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

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

Neuron 4850 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.2303. Min Act: -0.0001

Data Index: 967381 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1428. Min Act: -0.0001

Data Index: 913930 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.8115. Min Act: -0.0001

Data Index: 1309585 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.7980. Min Act: -0.0001

Data Index: 138846 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.7984. Min Act: -0.0001

Data Index: 542301 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.6950. Min Act: -0.0001

Data Index: 1127352 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.7697. Min Act: -0.0001

Data Index: 1255692 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.7347. Min Act: -0.0001

Data Index: 575745 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.7304. Min Act: -0.0001

Data Index: 677455 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.6611. Min Act: -0.0001

Data Index: 1067619 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.6588. Min Act: -0.0001

Data Index: 1134119 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.7904. Min Act: -0.0001

Data Index: 1329780 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.7469. Min Act: -0.0001

Data Index: 169727 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.6759. Min Act: -0.0001

Data Index: 29972 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.6378. Min Act: -0.0001

Data Index: 668038 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.6064. Min Act: -0.0001

Data Index: 694184 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.6700. Min Act: -0.0001

Data Index: 1179232 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.5953. Min Act: -0.0001

Data Index: 7553 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.5663. Min Act: -0.0001

Data Index: 305549 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.5998. Min Act: -0.0001

Data Index: 1085246 (C4 (Web Text))

Max Activating Token Index: 266