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

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

Neuron 2041 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: 2.8431. Min Range: -2.8431

Max Act: 2.7329. Min Act: -0.0000

Data Index: 239522 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.8431. Min Act: -0.0000

Data Index: 60980 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.8158. Min Act: -0.0000

Data Index: 1630206 (Python Code)

Max Activating Token Index: 970

Text #3

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.5509. Min Act: -0.0000

Data Index: 1583082 (Python Code)

Max Activating Token Index: 971

Text #4

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.5913. Min Act: -0.0000

Data Index: 949760 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.5526. Min Act: -0.0000

Data Index: 988422 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.6648. Min Act: -0.0000

Data Index: 1015930 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.2867. Min Act: -0.0000

Data Index: 1525693 (Python Code)

Max Activating Token Index: 938

Text #8

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.4903. Min Act: -0.0000

Data Index: 361137 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.3485. Min Act: -0.0001

Data Index: 1390766 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.2989. Min Act: -0.0000

Data Index: 326572 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.4133. Min Act: -0.0000

Data Index: 1351934 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.3072. Min Act: -0.0000

Data Index: 816825 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.3754. Min Act: -0.0000

Data Index: 488040 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.3705. Min Act: -0.0000

Data Index: 77472 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.3641. Min Act: -0.0000

Data Index: 933045 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.2575. Min Act: -0.0000

Data Index: 1559274 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.2470. Min Act: -0.0000

Data Index: 1518413 (Python Code)

Max Activating Token Index: 800

Text #18

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.4540. Min Act: -0.0000

Data Index: 1361191 (Python Code)

Max Activating Token Index: 904

Text #19

Max Range: 2.8431. Min Range: -2.8431

Max Act: 2.0801. Min Act: -0.0000

Data Index: 1601111 (Python Code)

Max Activating Token Index: 991