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

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

Neuron 661 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1136264 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1156040 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0581. Min Act: -0.0001

Data Index: 811289 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0620. Min Act: -0.0001

Data Index: 47355 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1018256 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0451. Min Act: -0.0001

Data Index: 37708 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0473. Min Act: -0.0001

Data Index: 715693 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0378. Min Act: -0.0001

Data Index: 220613 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0472. Min Act: -0.0001

Data Index: 87558 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0436. Min Act: -0.0001

Data Index: 849622 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0453. Min Act: -0.0001

Data Index: 872458 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0451. Min Act: -0.0001

Data Index: 16544 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0462. Min Act: -0.0001

Data Index: 1337246 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0372. Min Act: -0.0001

Data Index: 337961 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0412. Min Act: -0.0001

Data Index: 128613 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0431. Min Act: -0.0001

Data Index: 402658 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0434. Min Act: -0.0001

Data Index: 441739 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1264191 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1235925 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0391. Min Act: -0.0001

Data Index: 64762 (C4 (Web Text))

Max Activating Token Index: 198