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

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

Neuron 3238 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.2245. Min Act: -0.0000

Data Index: 320007 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1786. Min Act: -0.0000

Data Index: 820416 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.0957. Min Act: -0.0000

Data Index: 253059 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.0463. Min Act: -0.0000

Data Index: 798972 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.0012. Min Act: -0.0000

Data Index: 724010 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.9337. Min Act: -0.0000

Data Index: 394768 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.9278. Min Act: -0.0000

Data Index: 332819 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.9254. Min Act: -0.0000

Data Index: 593977 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.8867. Min Act: -0.0000

Data Index: 131110 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.9278. Min Act: -0.0000

Data Index: 19201 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.8935. Min Act: -0.0000

Data Index: 435973 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.8938. Min Act: -0.0000

Data Index: 347058 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1307044 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.9444. Min Act: -0.0000

Data Index: 311432 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.9090. Min Act: -0.0000

Data Index: 731684 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1006510 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.9292. Min Act: -0.0000

Data Index: 720227 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.9004. Min Act: -0.0000

Data Index: 898881 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.8415. Min Act: -0.0000

Data Index: 675153 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.2245. Min Range: -1.2245

Max Act: 0.8707. Min Act: -0.0000

Data Index: 689183 (C4 (Web Text))

Max Activating Token Index: 560