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

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

Neuron 1851 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.3108. Min Act: -0.0001

Data Index: 534982 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2676. Min Act: -0.0001

Data Index: 357759 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.3010. Min Act: -0.0000

Data Index: 278688 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2814. Min Act: -0.0000

Data Index: 716409 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.3098. Min Act: -0.0001

Data Index: 1020328 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.3027. Min Act: -0.0001

Data Index: 317772 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2924. Min Act: -0.0001

Data Index: 236993 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2772. Min Act: -0.0001

Data Index: 844695 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2503. Min Act: -0.0001

Data Index: 500802 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2519. Min Act: -0.0000

Data Index: 79946 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1078596 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2638. Min Act: -0.0001

Data Index: 1028968 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2244. Min Act: -0.0001

Data Index: 747120 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1099587 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2268. Min Act: -0.0000

Data Index: 170078 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2591. Min Act: -0.0000

Data Index: 827095 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2835. Min Act: -0.0000

Data Index: 419966 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2698. Min Act: -0.0000

Data Index: 960230 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2511. Min Act: -0.0001

Data Index: 1380295 (Python Code)

Max Activating Token Index: 347

Text #19

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1062627 (C4 (Web Text))

Max Activating Token Index: 742