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

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

Neuron 209 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8988. Min Act: -0.0000

Data Index: 859595 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1006021 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.7975. Min Act: -0.0000

Data Index: 287904 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.7939. Min Act: -0.0000

Data Index: 165112 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1197815 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.7019. Min Act: -0.0000

Data Index: 61665 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6645. Min Act: -0.0000

Data Index: 678502 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6760. Min Act: -0.0000

Data Index: 805301 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1391924 (Python Code)

Max Activating Token Index: 619

Text #9

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.7535. Min Act: -0.0000

Data Index: 109117 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.7308. Min Act: -0.0000

Data Index: 723193 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6590. Min Act: -0.0000

Data Index: 170678 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1496345 (Python Code)

Max Activating Token Index: 561

Text #13

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6588. Min Act: -0.0000

Data Index: 35986 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1378783 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6608. Min Act: -0.0000

Data Index: 313581 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1088550 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1569300 (Python Code)

Max Activating Token Index: 534

Text #18

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1514258 (Python Code)

Max Activating Token Index: 732

Text #19

Max Range: 0.8988. Min Range: -0.8988

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1416849 (Python Code)

Max Activating Token Index: 328