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

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

Neuron 1772 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0262. Min Range: -5.0262

Max Act: 5.0262. Min Act: -0.0000

Data Index: 1139194 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.9102. Min Act: -0.0000

Data Index: 251026 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 5.0262. Min Range: -5.0262

Max Act: 4.0106. Min Act: -0.0000

Data Index: 594424 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.3047. Min Act: -0.0000

Data Index: 559503 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.5151. Min Act: -0.0000

Data Index: 207154 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.8240. Min Act: -0.0000

Data Index: 630129 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.5961. Min Act: -0.0000

Data Index: 1154674 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.6469. Min Act: -0.0000

Data Index: 1029551 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 5.0262. Min Range: -5.0262

Max Act: 2.9878. Min Act: -0.0000

Data Index: 621763 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.2090. Min Act: -0.0000

Data Index: 400516 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.6013. Min Act: -0.0000

Data Index: 1096065 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.1097. Min Act: -0.0000

Data Index: 1248337 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.0916. Min Act: -0.0000

Data Index: 1125377 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.0938. Min Act: -0.0001

Data Index: 220499 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.2501. Min Act: -0.0000

Data Index: 71513 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 5.0262. Min Range: -5.0262

Max Act: 2.9160. Min Act: -0.0000

Data Index: 101049 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.2422. Min Act: -0.0000

Data Index: 507579 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 5.0262. Min Range: -5.0262

Max Act: 2.9068. Min Act: -0.0000

Data Index: 593825 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 5.0262. Min Range: -5.0262

Max Act: 3.0154. Min Act: -0.0000

Data Index: 921863 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 5.0262. Min Range: -5.0262

Max Act: 2.8816. Min Act: -0.0000

Data Index: 642732 (C4 (Web Text))

Max Activating Token Index: 386