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

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

Neuron 1084 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.8601. Min Act: -0.0001

Data Index: 1627184 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.8757. Min Act: -0.0002

Data Index: 660235 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.7643. Min Act: -0.0002

Data Index: 1261336 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.7595. Min Act: -0.0002

Data Index: 682745 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.7222. Min Act: -0.0002

Data Index: 865904 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.6626. Min Act: -0.0001

Data Index: 1315177 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.6299. Min Act: -0.0001

Data Index: 622674 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.6646. Min Act: -0.0001

Data Index: 422217 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.6216. Min Act: -0.0002

Data Index: 58834 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.6285. Min Act: -0.0002

Data Index: 545560 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.5347. Min Act: -0.0001

Data Index: 1352175 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.4881. Min Act: -0.0002

Data Index: 1048352 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.5010. Min Act: -0.0002

Data Index: 100007 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.5211. Min Act: -0.0001

Data Index: 11136 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.5197. Min Act: -0.0002

Data Index: 339515 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.5093. Min Act: -0.0001

Data Index: 279180 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.4877. Min Act: -0.0001

Data Index: 1341311 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.4774. Min Act: -0.0002

Data Index: 1136228 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.4715. Min Act: -0.0002

Data Index: 1220516 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.8757. Min Range: -1.8757

Max Act: 1.4784. Min Act: -0.0002

Data Index: 750209 (C4 (Web Text))

Max Activating Token Index: 877