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

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

Neuron 3273 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.3264. Min Act: -0.0000

Data Index: 639999 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1486742 (Python Code)

Max Activating Token Index: 741

Text #2

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1192572 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2191. Min Act: -0.0000

Data Index: 353203 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.1970. Min Act: -0.0000

Data Index: 753120 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2183. Min Act: -0.0000

Data Index: 411033 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1012035 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1042028 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2023. Min Act: -0.0000

Data Index: 903856 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.1913. Min Act: -0.0000

Data Index: 339677 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2208. Min Act: -0.0000

Data Index: 772609 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2220. Min Act: -0.0000

Data Index: 204188 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.1992. Min Act: -0.0000

Data Index: 938486 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.1766. Min Act: -0.0000

Data Index: 793154 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.1667. Min Act: -0.0000

Data Index: 390707 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.1662. Min Act: -0.0000

Data Index: 603973 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.1841. Min Act: -0.0000

Data Index: 249504 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.1898. Min Act: -0.0000

Data Index: 970310 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.1621. Min Act: -0.0000

Data Index: 876974 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.1805. Min Act: -0.0000

Data Index: 252219 (C4 (Web Text))

Max Activating Token Index: 849