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

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

Neuron 5039 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: 1.6734. Min Range: -1.6734

Max Act: 1.6734. Min Act: -0.0001

Data Index: 171550 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.9807. Min Act: -0.0000

Data Index: 986418 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.8604. Min Act: -0.0001

Data Index: 701488 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.8270. Min Act: -0.0000

Data Index: 217683 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.8879. Min Act: -0.0001

Data Index: 294535 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.8705. Min Act: -0.0001

Data Index: 1238941 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.8952. Min Act: -0.0000

Data Index: 67820 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1229025 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.7468. Min Act: -0.0001

Data Index: 161159 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.8505. Min Act: -0.0000

Data Index: 182789 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.7741. Min Act: -0.0001

Data Index: 82699 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.8257. Min Act: -0.0001

Data Index: 686540 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.8157. Min Act: -0.0001

Data Index: 1301155 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.7416. Min Act: -0.0001

Data Index: 218875 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.7627. Min Act: -0.0001

Data Index: 1078749 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.7635. Min Act: -0.0000

Data Index: 504588 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.7864. Min Act: -0.0001

Data Index: 1087734 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.7302. Min Act: -0.0001

Data Index: 868277 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.7378. Min Act: -0.0000

Data Index: 626415 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 1.6734. Min Range: -1.6734

Max Act: 0.7822. Min Act: -0.0001

Data Index: 342040 (C4 (Web Text))

Max Activating Token Index: 180