Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3418 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.4029. Min Act: -0.0001

Data Index: 93068 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.3655. Min Act: -0.0001

Data Index: 766710 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1690. Min Act: -0.0001

Data Index: 731896 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1624. Min Act: -0.0001

Data Index: 1288163 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0764. Min Act: -0.0001

Data Index: 1298577 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0699. Min Act: -0.0001

Data Index: 592484 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0902. Min Act: -0.0001

Data Index: 144410 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0506. Min Act: -0.0001

Data Index: 1352159 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0386. Min Act: -0.0001

Data Index: 927494 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0600. Min Act: -0.0001

Data Index: 1351466 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9679. Min Act: -0.0001

Data Index: 593080 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9548. Min Act: -0.0001

Data Index: 1147442 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9751. Min Act: -0.0001

Data Index: 1153928 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0039. Min Act: -0.0001

Data Index: 74122 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9666. Min Act: -0.0001

Data Index: 662559 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9281. Min Act: -0.0001

Data Index: 1119385 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9321. Min Act: -0.0001

Data Index: 551582 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9902. Min Act: -0.0001

Data Index: 1352071 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9601. Min Act: -0.0001

Data Index: 820434 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9366. Min Act: -0.0001

Data Index: 1110885 (C4 (Web Text))

Max Activating Token Index: 323