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

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

Neuron 5778 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0089. Min Range: -3.0089

Max Act: 3.0089. Min Act: -0.0000

Data Index: 981123 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.6438. Min Act: -0.0000

Data Index: 622648 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.5091. Min Act: -0.0000

Data Index: 938492 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.3895. Min Act: -0.0000

Data Index: 1092352 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.3266. Min Act: -0.0000

Data Index: 278426 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.1499. Min Act: -0.0000

Data Index: 1236629 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.1417. Min Act: -0.0000

Data Index: 998548 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 3.0089. Min Range: -3.0089

Max Act: 1.9896. Min Act: -0.0000

Data Index: 735544 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.0961. Min Act: -0.0000

Data Index: 354722 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.1943. Min Act: -0.0000

Data Index: 477887 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.0705. Min Act: -0.0000

Data Index: 963996 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.0585. Min Act: -0.0000

Data Index: 1074487 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 3.0089. Min Range: -3.0089

Max Act: 2.1161. Min Act: -0.0000

Data Index: 411313 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 3.0089. Min Range: -3.0089

Max Act: 1.9553. Min Act: -0.0000

Data Index: 368856 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 3.0089. Min Range: -3.0089

Max Act: 1.9052. Min Act: -0.0000

Data Index: 150811 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 3.0089. Min Range: -3.0089

Max Act: 1.9002. Min Act: -0.0000

Data Index: 296998 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.0089. Min Range: -3.0089

Max Act: 1.8763. Min Act: -0.0000

Data Index: 723721 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 3.0089. Min Range: -3.0089

Max Act: 1.8382. Min Act: -0.0000

Data Index: 1302537 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 3.0089. Min Range: -3.0089

Max Act: 1.8389. Min Act: -0.0000

Data Index: 359529 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 3.0089. Min Range: -3.0089

Max Act: 1.7783. Min Act: -0.0000

Data Index: 645649 (C4 (Web Text))

Max Activating Token Index: 457