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

Dataset: The Pile

Neuron 4988 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: 0.1458. Min Range: -0.1458

Max Act: 0.1458. Min Act: -0.0000

Data Index: 266235 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1349191 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1307. Min Act: -0.0000

Data Index: 444084 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1755668 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1285. Min Act: -0.0000

Data Index: 387401 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1303. Min Act: -0.0000

Data Index: 955892 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1029. Min Act: -0.0000

Data Index: 758858 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1089301 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1694185 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1051870 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1858988 (The Pile)

Max Activating Token Index: 674

Text #11

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1002. Min Act: -0.0000

Data Index: 341257 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1154139 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1511740 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1842841 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1469068 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1950604 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1991431 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1480666 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0913. Min Act: -0.0000

Data Index: 430677 (The Pile)

Max Activating Token Index: 81