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

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

Neuron 57 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.3342. Min Act: -0.0000

Data Index: 670619 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.2051. Min Act: -0.0000

Data Index: 552529 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.3342. Min Range: -1.3342

Max Act: 1.0610. Min Act: -0.0000

Data Index: 652451 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.9870. Min Act: -0.0000

Data Index: 123472 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.9510. Min Act: -0.0000

Data Index: 667927 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.8756. Min Act: -0.0000

Data Index: 1196551 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.8936. Min Act: -0.0000

Data Index: 541020 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.8643. Min Act: -0.0000

Data Index: 981597 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.8665. Min Act: -0.0000

Data Index: 953457 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.7936. Min Act: -0.0000

Data Index: 770281 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.7592. Min Act: -0.0000

Data Index: 217515 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.6791. Min Act: -0.0000

Data Index: 246766 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1304652 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.6338. Min Act: -0.0000

Data Index: 842356 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.6315. Min Act: -0.0000

Data Index: 823415 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.6091. Min Act: -0.0000

Data Index: 685817 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.6430. Min Act: 0.0000

Data Index: 561800 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1341464 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1035697 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.3342. Min Range: -1.3342

Max Act: 0.5815. Min Act: -0.0000

Data Index: 679325 (C4 (Web Text))

Max Activating Token Index: 332