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

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

Neuron 2677 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1137596 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1652. Min Act: -0.0001

Data Index: 564790 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1654. Min Act: -0.0001

Data Index: 736962 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0001

Data Index: 949236 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1551. Min Act: -0.0001

Data Index: 782568 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1581. Min Act: -0.0001

Data Index: 977840 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1046144 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1629. Min Act: -0.0001

Data Index: 724120 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1085043 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1376. Min Act: -0.0001

Data Index: 36577 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1506. Min Act: -0.0001

Data Index: 535798 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1492. Min Act: -0.0001

Data Index: 330014 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1494. Min Act: -0.0001

Data Index: 858789 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1435. Min Act: -0.0001

Data Index: 988750 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1386. Min Act: -0.0001

Data Index: 433290 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1427. Min Act: -0.0001

Data Index: 966109 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1246976 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1413. Min Act: -0.0001

Data Index: 167759 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1459. Min Act: -0.0001

Data Index: 419064 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1336448 (C4 (Web Text))

Max Activating Token Index: 67