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

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

Neuron 4629 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0585. Min Range: -3.0585

Max Act: 3.0585. Min Act: -0.0000

Data Index: 987422 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 3.0585. Min Range: -3.0585

Max Act: 2.5429. Min Act: -0.0000

Data Index: 905794 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 3.0585. Min Range: -3.0585

Max Act: 2.3878. Min Act: -0.0000

Data Index: 1215802 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 3.0585. Min Range: -3.0585

Max Act: 2.3134. Min Act: -0.0000

Data Index: 1342527 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 3.0585. Min Range: -3.0585

Max Act: 2.2602. Min Act: -0.0000

Data Index: 349226 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 3.0585. Min Range: -3.0585

Max Act: 2.1124. Min Act: -0.0000

Data Index: 257414 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 3.0585. Min Range: -3.0585

Max Act: 2.0423. Min Act: -0.0000

Data Index: 40601 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.9349. Min Act: -0.0000

Data Index: 1076969 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 3.0585. Min Range: -3.0585

Max Act: 2.0130. Min Act: -0.0000

Data Index: 1178676 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.8361. Min Act: -0.0000

Data Index: 892086 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.8696. Min Act: -0.0000

Data Index: 1265924 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.7659. Min Act: -0.0000

Data Index: 1028131 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.8483. Min Act: -0.0000

Data Index: 1341023 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.8077. Min Act: -0.0000

Data Index: 1056193 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.7727. Min Act: -0.0000

Data Index: 655439 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.8665. Min Act: -0.0000

Data Index: 640085 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.6681. Min Act: -0.0000

Data Index: 765767 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.7618. Min Act: -0.0000

Data Index: 1227815 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.7064. Min Act: -0.0000

Data Index: 860968 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 3.0585. Min Range: -3.0585

Max Act: 1.6496. Min Act: -0.0000

Data Index: 630269 (C4 (Web Text))

Max Activating Token Index: 862