Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2900 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.3075. Min Act: -0.0000

Data Index: 638493 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2719. Min Act: -0.0000

Data Index: 179441 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2557. Min Act: -0.0000

Data Index: 201111 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1212555 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2420. Min Act: -0.0000

Data Index: 31226 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2787. Min Act: -0.0000

Data Index: 740557 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2535. Min Act: -0.0000

Data Index: 80191 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1196899 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2406. Min Act: -0.0000

Data Index: 725988 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2399. Min Act: -0.0000

Data Index: 654669 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2251. Min Act: -0.0000

Data Index: 942086 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2089. Min Act: -0.0000

Data Index: 349578 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1306523 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1235525 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1088044 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2044. Min Act: -0.0000

Data Index: 351344 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2114. Min Act: -0.0000

Data Index: 253154 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2153. Min Act: -0.0000

Data Index: 753961 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2012. Min Act: -0.0000

Data Index: 877224 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.1928. Min Act: -0.0000

Data Index: 115272 (C4 (Web Text))

Max Activating Token Index: 210