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

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

Neuron 1773 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.6618. Min Act: -0.0000

Data Index: 26102 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.3387. Min Act: -0.0000

Data Index: 525467 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.6618. Min Range: -1.6618

Max Act: 1.1713. Min Act: -0.0000

Data Index: 998410 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.9200. Min Act: -0.0000

Data Index: 656365 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.8630. Min Act: -0.0000

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.5495. Min Act: -0.0000

Data Index: 970036 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.8476. Min Act: -0.0000

Data Index: 949700 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1203657 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1355432 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.6924. Min Act: -0.0000

Data Index: 780381 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.7103. Min Act: -0.0000

Data Index: 521262 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1122892 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1125500 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.6957. Min Act: -0.0000

Data Index: 343397 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.7377. Min Act: -0.0000

Data Index: 442636 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.7127. Min Act: -0.0000

Data Index: 97560 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.6384. Min Act: -0.0000

Data Index: 386345 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.6385. Min Act: -0.0000

Data Index: 371840 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1156523 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 1.6618. Min Range: -1.6618

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1003154 (C4 (Web Text))

Max Activating Token Index: 503