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

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

Neuron 1951 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.1067. Min Act: -0.0001

Data Index: 614026 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0988. Min Act: -0.0001

Data Index: 866293 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0918. Min Act: -0.0001

Data Index: 517194 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0875. Min Act: -0.0001

Data Index: 127240 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1590256 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0986. Min Act: -0.0000

Data Index: 349148 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0871. Min Act: -0.0001

Data Index: 332763 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0875. Min Act: -0.0001

Data Index: 103580 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0928. Min Act: -0.0001

Data Index: 47140 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1396607 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0836. Min Act: -0.0001

Data Index: 352278 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1160968 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0863. Min Act: -0.0001

Data Index: 44449 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0859. Min Act: 0.0000

Data Index: 191521 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0818. Min Act: -0.0001

Data Index: 3084 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0841. Min Act: -0.0000

Data Index: 599875 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1166730 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1154262 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0818. Min Act: -0.0001

Data Index: 515171 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0760. Min Act: -0.0001

Data Index: 197974 (C4 (Web Text))

Max Activating Token Index: 278