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

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

Neuron 1395 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1954. Min Act: -0.0001

Data Index: 881602 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1944. Min Act: -0.0001

Data Index: 139767 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1858. Min Act: -0.0001

Data Index: 521871 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1960. Min Act: -0.0001

Data Index: 733928 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1129199 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1880. Min Act: -0.0001

Data Index: 1023238 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1718. Min Act: -0.0001

Data Index: 678984 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1768. Min Act: -0.0001

Data Index: 270561 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1703. Min Act: -0.0001

Data Index: 6104 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1304612 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1752. Min Act: -0.0001

Data Index: 1107510 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1993. Min Act: -0.0001

Data Index: 149928 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1901. Min Act: -0.0001

Data Index: 517692 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1607. Min Act: -0.0001

Data Index: 868511 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1591. Min Act: -0.0001

Data Index: 563555 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1589. Min Act: -0.0001

Data Index: 345626 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1526. Min Act: -0.0001

Data Index: 210119 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1024119 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1615. Min Act: -0.0001

Data Index: 831859 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.1993. Min Range: -0.1993

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1220034 (C4 (Web Text))

Max Activating Token Index: 115