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

Dataset: The Pile

Neuron 3426 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1499. Min Act: -0.0000

Data Index: 245024 (The Pile)

Max Activating Token Index: 966

Text #1

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1976264 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1470. Min Act: -0.0000

Data Index: 275816 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1430138 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1299. Min Act: -0.0000

Data Index: 258950 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1244. Min Act: -0.0000

Data Index: 156074 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1274. Min Act: -0.0000

Data Index: 444647 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1232. Min Act: -0.0000

Data Index: 742567 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1193. Min Act: -0.0000

Data Index: 890253 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1517584 (The Pile)

Max Activating Token Index: 878

Text #10

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1100. Min Act: -0.0000

Data Index: 6644 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1047. Min Act: -0.0000

Data Index: 782055 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1749736 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1045. Min Act: -0.0000

Data Index: 998973 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1003. Min Act: -0.0000

Data Index: 946641 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1705261 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1729047 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1879687 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1582877 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.0932. Min Act: -0.0000

Data Index: 392301 (The Pile)

Max Activating Token Index: 104