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

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

Neuron 3869 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.6306. Min Act: 0.0002

Data Index: 1027892 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.6057. Min Act: -0.0000

Data Index: 443806 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5227. Min Act: 0.0000

Data Index: 186974 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5131. Min Act: -0.0000

Data Index: 389514 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1317961 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5077. Min Act: -0.0000

Data Index: 262478 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4984. Min Act: -0.0000

Data Index: 484239 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5131. Min Act: 0.0000

Data Index: 1320003 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4723. Min Act: -0.0000

Data Index: 982093 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1027395 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4567. Min Act: -0.0000

Data Index: 78891 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4652. Min Act: -0.0000

Data Index: 715873 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4783. Min Act: -0.0000

Data Index: 12321 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4583. Min Act: 0.0000

Data Index: 125329 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4545. Min Act: -0.0000

Data Index: 330999 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4539. Min Act: -0.0000

Data Index: 530813 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4481. Min Act: 0.0000

Data Index: 944539 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1165226 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4552. Min Act: -0.0000

Data Index: 232690 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4140. Min Act: -0.0000

Data Index: 959194 (C4 (Web Text))

Max Activating Token Index: 268