Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1277 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1255. Min Range: -1.1255

Max Act: 1.1255. Min Act: -0.0000

Data Index: 1638922 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 1.1255. Min Range: -1.1255

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1388390 (Python Code)

Max Activating Token Index: 281

Text #2

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1461227 (Python Code)

Max Activating Token Index: 195

Text #3

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1501936 (Python Code)

Max Activating Token Index: 470

Text #4

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1574416 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1614767 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1396877 (Python Code)

Max Activating Token Index: 378

Text #7

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1648198 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1598814 (Python Code)

Max Activating Token Index: 425

Text #9

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1367582 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1608807 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1533027 (Python Code)

Max Activating Token Index: 681

Text #12

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1602321 (Python Code)

Max Activating Token Index: 926

Text #13

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1646750 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1622393 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1618154 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1377652 (Python Code)

Max Activating Token Index: 806

Text #17

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1516559 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1617812 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 1.1255. Min Range: -1.1255

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1395868 (Python Code)

Max Activating Token Index: 33