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

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

Neuron 4582 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.2770. Min Act: -0.0001

Data Index: 851290 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.5084. Min Act: -0.0001

Data Index: 36967 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.3182. Min Act: -0.0001

Data Index: 617897 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.3613. Min Act: -0.0001

Data Index: 43804 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.3266. Min Act: -0.0001

Data Index: 175574 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.2309. Min Act: -0.0000

Data Index: 547264 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.2762. Min Act: -0.0001

Data Index: 741646 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.3561. Min Act: -0.0001

Data Index: 473687 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.2052. Min Act: -0.0001

Data Index: 8379 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.2533. Min Act: -0.0001

Data Index: 894120 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.2218. Min Act: -0.0001

Data Index: 1306557 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.2097. Min Act: -0.0001

Data Index: 1215787 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.2384. Min Act: -0.0001

Data Index: 980384 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.1629. Min Act: -0.0001

Data Index: 274230 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1146371 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.2016. Min Act: -0.0001

Data Index: 1283771 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.1918. Min Act: -0.0000

Data Index: 45265 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.1379. Min Act: -0.0001

Data Index: 20686 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.2221. Min Act: -0.0001

Data Index: 300459 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.5084. Min Range: -1.5084

Max Act: 1.0393. Min Act: -0.0001

Data Index: 1069683 (C4 (Web Text))

Max Activating Token Index: 221