Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4909 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1616. Min Range: -3.1616

Max Act: 3.1616. Min Act: -0.0001

Data Index: 339983 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.9324. Min Act: -0.0000

Data Index: 777850 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.5261. Min Act: -0.0001

Data Index: 1508838 (Python Code)

Max Activating Token Index: 512

Text #3

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.4827. Min Act: -0.0000

Data Index: 272763 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.4151. Min Act: -0.0001

Data Index: 1611553 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.5919. Min Act: -0.0000

Data Index: 46709 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.3254. Min Act: -0.0000

Data Index: 1270453 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.2145. Min Act: -0.0000

Data Index: 1223517 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.0878. Min Act: -0.0001

Data Index: 1008287 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.1781. Min Act: -0.0001

Data Index: 531523 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 3.1616. Min Range: -3.1616

Max Act: 1.9414. Min Act: -0.0000

Data Index: 542856 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.1554. Min Act: -0.0000

Data Index: 693737 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.1245. Min Act: -0.0000

Data Index: 746043 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.2282. Min Act: -0.0000

Data Index: 614574 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.0979. Min Act: -0.0000

Data Index: 464011 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.0929. Min Act: -0.0000

Data Index: 475858 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.0515. Min Act: -0.0000

Data Index: 1217235 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 3.1616. Min Range: -3.1616

Max Act: 2.1408. Min Act: -0.0000

Data Index: 137217 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 3.1616. Min Range: -3.1616

Max Act: 1.8885. Min Act: -0.0000

Data Index: 679893 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 3.1616. Min Range: -3.1616

Max Act: 1.9949. Min Act: -0.0000

Data Index: 326836 (C4 (Web Text))

Max Activating Token Index: 503