Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3789 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9365. Min Act: -0.0001

Data Index: 1415770 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8728. Min Act: -0.0001

Data Index: 1592265 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9229. Min Act: -0.0001

Data Index: 1425894 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9228. Min Act: -0.0001

Data Index: 1599278 (Python Code)

Max Activating Token Index: 768

Text #4

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7795. Min Act: -0.0001

Data Index: 744526 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7901. Min Act: -0.0001

Data Index: 1629234 (Python Code)

Max Activating Token Index: 476

Text #6

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7895. Min Act: -0.0001

Data Index: 307852 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7821. Min Act: -0.0001

Data Index: 685037 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7299. Min Act: -0.0001

Data Index: 1491354 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7734. Min Act: -0.0001

Data Index: 231248 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7289. Min Act: -0.0001

Data Index: 769 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7747. Min Act: -0.0001

Data Index: 1461124 (Python Code)

Max Activating Token Index: 895

Text #12

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7173. Min Act: -0.0001

Data Index: 1649194 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7221. Min Act: -0.0001

Data Index: 1078825 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6658. Min Act: -0.0001

Data Index: 883716 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1610324 (Python Code)

Max Activating Token Index: 493

Text #16

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7255. Min Act: -0.0001

Data Index: 1460220 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7212. Min Act: -0.0001

Data Index: 1491176 (Python Code)

Max Activating Token Index: 769

Text #18

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7194. Min Act: -0.0001

Data Index: 948964 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6625. Min Act: -0.0001

Data Index: 296903 (C4 (Web Text))

Max Activating Token Index: 397