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

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

Neuron 3523 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: 0.5161. Min Range: -0.5161

Max Act: 0.4918. Min Act: -0.0000

Data Index: 837706 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1016074 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4624. Min Act: -0.0001

Data Index: 980689 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4855. Min Act: -0.0000

Data Index: 887887 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4541. Min Act: -0.0001

Data Index: 1017181 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1034360 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4615. Min Act: -0.0000

Data Index: 55246 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4529. Min Act: -0.0001

Data Index: 590693 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4478. Min Act: -0.0000

Data Index: 964350 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4600. Min Act: -0.0001

Data Index: 938748 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1008819 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4085. Min Act: -0.0001

Data Index: 243831 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4618. Min Act: -0.0001

Data Index: 800217 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4648. Min Act: -0.0001

Data Index: 1044501 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.3954. Min Act: -0.0001

Data Index: 1052584 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.5161. Min Act: -0.0001

Data Index: 24068 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4275. Min Act: -0.0001

Data Index: 1298817 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4148. Min Act: -0.0000

Data Index: 799572 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1041089 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1322721 (C4 (Web Text))

Max Activating Token Index: 53