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

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

Neuron 882 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: 4.5402. Min Range: -4.5402

Max Act: 4.3336. Min Act: -0.0000

Data Index: 1339323 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 4.5402. Min Range: -4.5402

Max Act: 4.4885. Min Act: -0.0000

Data Index: 962526 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 4.5402. Min Range: -4.5402

Max Act: 4.5402. Min Act: -0.0000

Data Index: 1104011 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.8221. Min Act: -0.0000

Data Index: 310697 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 4.5402. Min Range: -4.5402

Max Act: 4.1495. Min Act: -0.0000

Data Index: 181424 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 4.5402. Min Range: -4.5402

Max Act: 4.1367. Min Act: -0.0000

Data Index: 556408 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 4.5402. Min Range: -4.5402

Max Act: 4.1082. Min Act: -0.0000

Data Index: 247923 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 4.5402. Min Range: -4.5402

Max Act: 4.1301. Min Act: -0.0000

Data Index: 115854 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.7835. Min Act: -0.0000

Data Index: 280934 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 4.5402. Min Range: -4.5402

Max Act: 4.2525. Min Act: -0.0000

Data Index: 1266329 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.8839. Min Act: -0.0000

Data Index: 1181206 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.6984. Min Act: -0.0000

Data Index: 1275494 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.9883. Min Act: -0.0000

Data Index: 933543 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.7861. Min Act: -0.0000

Data Index: 941800 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.5904. Min Act: -0.0000

Data Index: 855878 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.5822. Min Act: -0.0000

Data Index: 47846 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.7467. Min Act: -0.0000

Data Index: 549462 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.5635. Min Act: -0.0000

Data Index: 976196 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.8556. Min Act: -0.0000

Data Index: 443588 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 4.5402. Min Range: -4.5402

Max Act: 3.3661. Min Act: -0.0000

Data Index: 200541 (C4 (Web Text))

Max Activating Token Index: 80