Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 997 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1055922 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0535. Min Act: -0.0001

Data Index: 835918 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1171233 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0514. Min Act: -0.0001

Data Index: 752655 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0511. Min Act: -0.0001

Data Index: 50393 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0511. Min Act: -0.0001

Data Index: 26943 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1348712 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0446. Min Act: -0.0001

Data Index: 999457 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0479. Min Act: -0.0001

Data Index: 255181 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0427. Min Act: -0.0001

Data Index: 433164 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0412. Min Act: -0.0001

Data Index: 580901 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1040901 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0409. Min Act: -0.0001

Data Index: 513965 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0404. Min Act: -0.0001

Data Index: 337993 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0433. Min Act: -0.0001

Data Index: 184907 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1200421 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1145857 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1356853 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0408. Min Act: -0.0001

Data Index: 931377 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0408. Min Act: -0.0001

Data Index: 105226 (C4 (Web Text))

Max Activating Token Index: 27