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

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

Neuron 6060 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4471. Min Range: -2.4471

Max Act: 2.4471. Min Act: -0.0000

Data Index: 1428753 (Python Code)

Max Activating Token Index: 97

Text #1

Max Range: 2.4471. Min Range: -2.4471

Max Act: 2.1794. Min Act: -0.0000

Data Index: 282611 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.8683. Min Act: -0.0000

Data Index: 916134 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.7658. Min Act: -0.0000

Data Index: 711725 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.9431. Min Act: -0.0000

Data Index: 38448 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.9477. Min Act: -0.0000

Data Index: 814550 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.9551. Min Act: -0.0000

Data Index: 94510 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.8538. Min Act: -0.0000

Data Index: 1555644 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.7446. Min Act: -0.0000

Data Index: 762643 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.8349. Min Act: -0.0000

Data Index: 412081 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.6828. Min Act: -0.0000

Data Index: 1453326 (Python Code)

Max Activating Token Index: 905

Text #11

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.7690. Min Act: -0.0000

Data Index: 1288572 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.7260. Min Act: -0.0000

Data Index: 1649583 (Python Code)

Max Activating Token Index: 584

Text #13

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.5395. Min Act: -0.0000

Data Index: 1481213 (Python Code)

Max Activating Token Index: 856

Text #14

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.4964. Min Act: -0.0000

Data Index: 1565873 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.6791. Min Act: -0.0000

Data Index: 1426146 (Python Code)

Max Activating Token Index: 692

Text #16

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.6504. Min Act: -0.0000

Data Index: 996863 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.5405. Min Act: -0.0000

Data Index: 866862 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1469835 (Python Code)

Max Activating Token Index: 146

Text #19

Max Range: 2.4471. Min Range: -2.4471

Max Act: 1.6213. Min Act: -0.0000

Data Index: 561696 (C4 (Web Text))

Max Activating Token Index: 549