Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1844 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1978. Min Act: -0.0003

Data Index: 998298 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.2119. Min Act: -0.0003

Data Index: 1207887 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1930. Min Act: -0.0003

Data Index: 1124557 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1719. Min Act: -0.0003

Data Index: 915607 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1753. Min Act: -0.0003

Data Index: 428478 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.2144. Min Act: -0.0003

Data Index: 208098 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1509. Min Act: -0.0003

Data Index: 38960 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1558. Min Act: -0.0003

Data Index: 361663 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1549. Min Act: -0.0003

Data Index: 361054 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1621. Min Act: -0.0003

Data Index: 288929 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1636. Min Act: -0.0003

Data Index: 941527 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1549. Min Act: -0.0003

Data Index: 599572 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1592. Min Act: -0.0003

Data Index: 1180507 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1629. Min Act: -0.0003

Data Index: 646213 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1555. Min Act: -0.0003

Data Index: 580816 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1570. Min Act: -0.0003

Data Index: 412882 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1676. Min Act: -0.0003

Data Index: 1249769 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1570. Min Act: -0.0003

Data Index: 923547 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1565. Min Act: -0.0003

Data Index: 1136926 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1558. Min Act: -0.0003

Data Index: 501889 (C4 (Web Text))

Max Activating Token Index: 414