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

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

Neuron 3581 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1511333 (Python Code)

Max Activating Token Index: 478

Text #1

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1643883 (Python Code)

Max Activating Token Index: 462

Text #2

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1647765 (Python Code)

Max Activating Token Index: 498

Text #3

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1582517 (Python Code)

Max Activating Token Index: 258

Text #4

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1493243 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1497427 (Python Code)

Max Activating Token Index: 508

Text #6

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1623275 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1523418 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1630300 (Python Code)

Max Activating Token Index: 810

Text #9

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1521543 (Python Code)

Max Activating Token Index: 840

Text #10

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1517109 (Python Code)

Max Activating Token Index: 180

Text #11

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1628349 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4972. Min Act: -0.0000

Data Index: 438304 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5010. Min Act: -0.0000

Data Index: 222818 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4927. Min Act: -0.0000

Data Index: 40096 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1399125 (Python Code)

Max Activating Token Index: 156

Text #16

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4797. Min Act: 0.0000

Data Index: 1289477 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1369605 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1598685 (Python Code)

Max Activating Token Index: 305

Text #19

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4586. Min Act: -0.0000

Data Index: 354474 (C4 (Web Text))

Max Activating Token Index: 917