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

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

Neuron 1046 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: 2.1007. Min Range: -2.1007

Max Act: 1.9891. Min Act: -0.0001

Data Index: 1416403 (Python Code)

Max Activating Token Index: 746

Text #1

Max Range: 2.1007. Min Range: -2.1007

Max Act: 2.0205. Min Act: -0.0000

Data Index: 1448659 (Python Code)

Max Activating Token Index: 760

Text #2

Max Range: 2.1007. Min Range: -2.1007

Max Act: 2.1007. Min Act: -0.0000

Data Index: 1365765 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1633227 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 2.1007. Min Range: -2.1007

Max Act: 2.0338. Min Act: -0.0001

Data Index: 1535060 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.9496. Min Act: -0.0001

Data Index: 1598138 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.9019. Min Act: -0.0000

Data Index: 1637553 (Python Code)

Max Activating Token Index: 375

Text #7

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.9721. Min Act: -0.0001

Data Index: 1554992 (Python Code)

Max Activating Token Index: 239

Text #8

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.9171. Min Act: -0.0000

Data Index: 1603844 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.7271. Min Act: -0.0000

Data Index: 1582696 (Python Code)

Max Activating Token Index: 805

Text #10

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1392060 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.4282. Min Act: -0.0000

Data Index: 569192 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.7888. Min Act: -0.0000

Data Index: 1638457 (Python Code)

Max Activating Token Index: 866

Text #13

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.6032. Min Act: -0.0001

Data Index: 1565352 (Python Code)

Max Activating Token Index: 862

Text #14

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.6002. Min Act: -0.0000

Data Index: 895343 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.5479. Min Act: -0.0000

Data Index: 1653109 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.6302. Min Act: -0.0001

Data Index: 1545956 (Python Code)

Max Activating Token Index: 354

Text #17

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.4619. Min Act: -0.0000

Data Index: 777676 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.6892. Min Act: -0.0001

Data Index: 1639551 (Python Code)

Max Activating Token Index: 615

Text #19

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.6073. Min Act: -0.0001

Data Index: 1395706 (Python Code)

Max Activating Token Index: 968