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

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

Neuron 1360 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: 0.9344. Min Range: -0.9344

Max Act: 0.9344. Min Act: -0.0000

Data Index: 767089 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.9084. Min Act: -0.0000

Data Index: 89901 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8761. Min Act: -0.0000

Data Index: 6003 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8924. Min Act: -0.0000

Data Index: 239365 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.7580. Min Act: -0.0000

Data Index: 982138 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.7434. Min Act: -0.0000

Data Index: 825141 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8001. Min Act: -0.0000

Data Index: 298432 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.7522. Min Act: -0.0000

Data Index: 138799 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1653709 (Python Code)

Max Activating Token Index: 44

Text #9

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1333147 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1385531 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1437552 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.6674. Min Act: -0.0000

Data Index: 324085 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.6651. Min Act: -0.0000

Data Index: 457725 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1365163 (Python Code)

Max Activating Token Index: 1015

Text #15

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1392153 (Python Code)

Max Activating Token Index: 450

Text #16

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.6399. Min Act: -0.0000

Data Index: 847486 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1439263 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1585022 (Python Code)

Max Activating Token Index: 656

Text #19

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1409405 (Python Code)

Max Activating Token Index: 738