Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3707 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.3147. Min Act: -0.0000

Data Index: 500558 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2594. Min Act: -0.0000

Data Index: 918673 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1391342 (Python Code)

Max Activating Token Index: 931

Text #3

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1374480 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2454. Min Act: -0.0000

Data Index: 569848 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2339. Min Act: -0.0000

Data Index: 311865 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2260. Min Act: -0.0000

Data Index: 640824 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1403729 (Python Code)

Max Activating Token Index: 563

Text #8

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2294. Min Act: -0.0000

Data Index: 850520 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2186. Min Act: -0.0000

Data Index: 767270 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1523641 (Python Code)

Max Activating Token Index: 910

Text #11

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2223. Min Act: -0.0000

Data Index: 196666 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2112. Min Act: -0.0000

Data Index: 303243 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1998. Min Act: -0.0000

Data Index: 806924 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1865. Min Act: -0.0000

Data Index: 802770 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1584203 (Python Code)

Max Activating Token Index: 307

Text #16

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1607255 (Python Code)

Max Activating Token Index: 577

Text #17

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1848. Min Act: -0.0000

Data Index: 735670 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1479859 (Python Code)

Max Activating Token Index: 335

Text #19

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1503036 (Python Code)

Max Activating Token Index: 687