Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5747 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0709. Min Act: -0.0001

Data Index: 877314 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0661. Min Act: -0.0001

Data Index: 59214 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0632. Min Act: -0.0001

Data Index: 241493 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0001

Data Index: 278109 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1127364 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1336989 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0628. Min Act: -0.0001

Data Index: 342564 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0571. Min Act: -0.0001

Data Index: 780317 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1312536 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1296601 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0574. Min Act: -0.0001

Data Index: 400199 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1197727 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0550. Min Act: -0.0001

Data Index: 337956 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1129258 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1000605 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1317436 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1379522 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0511. Min Act: -0.0001

Data Index: 528490 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0527. Min Act: -0.0001

Data Index: 910139 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1166542 (C4 (Web Text))

Max Activating Token Index: 211