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

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

Neuron 2812 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: 0.2537. Min Range: -0.2537

Max Act: 0.2537. Min Act: -0.0000

Data Index: 710953 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1937. Min Act: -0.0000

Data Index: 447232 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2038. Min Act: -0.0000

Data Index: 269569 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1940. Min Act: -0.0000

Data Index: 483887 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1796. Min Act: -0.0000

Data Index: 950266 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1988. Min Act: -0.0000

Data Index: 139830 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2020. Min Act: -0.0000

Data Index: 106498 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1814. Min Act: -0.0000

Data Index: 783375 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1765. Min Act: -0.0000

Data Index: 118972 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1662. Min Act: -0.0000

Data Index: 814005 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1665. Min Act: -0.0000

Data Index: 222912 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1384. Min Act: -0.0000

Data Index: 321141 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1305064 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1329. Min Act: -0.0000

Data Index: 245851 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1304. Min Act: -0.0000

Data Index: 421902 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1171598 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1238. Min Act: -0.0000

Data Index: 790461 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1155564 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1133. Min Act: -0.0000

Data Index: 377598 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1147. Min Act: -0.0000

Data Index: 986844 (C4 (Web Text))

Max Activating Token Index: 643