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

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

Neuron 1843 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.7294. Min Act: -0.0001

Data Index: 455492 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.7287. Min Act: -0.0001

Data Index: 1191562 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.7753. Min Act: -0.0001

Data Index: 1218030 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.5994. Min Act: -0.0001

Data Index: 628245 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.6935. Min Act: -0.0001

Data Index: 1179749 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.6265. Min Act: -0.0001

Data Index: 611752 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.7214. Min Act: -0.0001

Data Index: 1103709 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.4543. Min Act: -0.0001

Data Index: 817797 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.4664. Min Act: -0.0001

Data Index: 618503 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.4629. Min Act: -0.0001

Data Index: 1273775 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.5196. Min Act: -0.0001

Data Index: 657793 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.4864. Min Act: -0.0001

Data Index: 118335 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.5322. Min Act: -0.0001

Data Index: 700239 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.4960. Min Act: -0.0001

Data Index: 1103783 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.5796. Min Act: -0.0001

Data Index: 1518684 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.4776. Min Act: -0.0001

Data Index: 1332263 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.5613. Min Act: -0.0001

Data Index: 1346701 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.4078. Min Act: -0.0001

Data Index: 287834 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.3728. Min Act: -0.0001

Data Index: 393576 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 1.7753. Min Range: -1.7753

Max Act: 1.5741. Min Act: -0.0001

Data Index: 507861 (C4 (Web Text))

Max Activating Token Index: 502