Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5297 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1989. Min Range: -3.1989

Max Act: 3.1989. Min Act: -0.0000

Data Index: 794501 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.8491. Min Act: -0.0000

Data Index: 898493 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.8085. Min Act: -0.0000

Data Index: 1218346 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.6285. Min Act: -0.0000

Data Index: 114614 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.6476. Min Act: -0.0000

Data Index: 951255 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.5962. Min Act: -0.0000

Data Index: 1337981 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.4751. Min Act: -0.0000

Data Index: 423850 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.2015. Min Act: -0.0000

Data Index: 741565 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.0751. Min Act: -0.0000

Data Index: 870068 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.1429. Min Act: -0.0000

Data Index: 492790 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.1167. Min Act: -0.0000

Data Index: 385864 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.0049. Min Act: -0.0000

Data Index: 995050 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.0730. Min Act: -0.0000

Data Index: 798550 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 3.1989. Min Range: -3.1989

Max Act: 1.9626. Min Act: -0.0000

Data Index: 505322 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.0157. Min Act: -0.0000

Data Index: 1030130 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 3.1989. Min Range: -3.1989

Max Act: 1.9969. Min Act: -0.0000

Data Index: 928582 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.0040. Min Act: -0.0000

Data Index: 1034607 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 3.1989. Min Range: -3.1989

Max Act: 1.9831. Min Act: -0.0000

Data Index: 546748 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 3.1989. Min Range: -3.1989

Max Act: 1.8637. Min Act: -0.0000

Data Index: 440644 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 3.1989. Min Range: -3.1989

Max Act: 2.0644. Min Act: -0.0000

Data Index: 845295 (C4 (Web Text))

Max Activating Token Index: 975