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

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

Neuron 5065 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: 3.6864. Min Range: -3.6864

Max Act: 3.6864. Min Act: -0.0000

Data Index: 1163503 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.8486. Min Act: -0.0000

Data Index: 807646 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.4512. Min Act: -0.0000

Data Index: 848311 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.0243. Min Act: -0.0000

Data Index: 293068 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.9598. Min Act: -0.0001

Data Index: 330008 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.9687. Min Act: -0.0000

Data Index: 827175 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.6736. Min Act: -0.0001

Data Index: 498703 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.7723. Min Act: -0.0001

Data Index: 914117 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.9595. Min Act: -0.0000

Data Index: 873938 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.2253. Min Act: -0.0000

Data Index: 178544 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 3.6864. Min Range: -3.6864

Max Act: 3.0104. Min Act: -0.0000

Data Index: 259223 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.6140. Min Act: -0.0000

Data Index: 980678 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.3394. Min Act: -0.0000

Data Index: 1129664 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.2059. Min Act: -0.0001

Data Index: 1126078 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.8081. Min Act: -0.0000

Data Index: 420699 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.5232. Min Act: -0.0001

Data Index: 603232 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.2859. Min Act: -0.0000

Data Index: 224514 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.6356. Min Act: -0.0000

Data Index: 999725 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.3544. Min Act: -0.0000

Data Index: 1234352 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 3.6864. Min Range: -3.6864

Max Act: 2.2143. Min Act: -0.0000

Data Index: 743563 (C4 (Web Text))

Max Activating Token Index: 358