Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1695 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.8314. Min Act: -0.0001

Data Index: 346175 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6889. Min Act: -0.0001

Data Index: 317385 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6439. Min Act: -0.0001

Data Index: 972129 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6203. Min Act: -0.0000

Data Index: 405344 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6633. Min Act: -0.0001

Data Index: 1336296 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6074. Min Act: -0.0001

Data Index: 600425 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6029. Min Act: -0.0001

Data Index: 685923 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6056. Min Act: -0.0000

Data Index: 78442 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5669. Min Act: -0.0001

Data Index: 848856 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5478. Min Act: -0.0001

Data Index: 809557 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5631. Min Act: -0.0001

Data Index: 558048 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1356618 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5741. Min Act: -0.0000

Data Index: 382808 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5743. Min Act: -0.0000

Data Index: 777245 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6005. Min Act: -0.0000

Data Index: 73396 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5816. Min Act: -0.0001

Data Index: 872500 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5620. Min Act: -0.0001

Data Index: 1249585 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5212. Min Act: -0.0000

Data Index: 810793 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5621. Min Act: -0.0000

Data Index: 567153 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.5484. Min Act: -0.0000

Data Index: 598371 (C4 (Web Text))

Max Activating Token Index: 19