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

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

Neuron 2354 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: 0.9073. Min Range: -0.9073

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1537428 (Python Code)

Max Activating Token Index: 447

Text #1

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1455372 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1650621 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1525622 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1540038 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1427312 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1457938 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1617854 (Python Code)

Max Activating Token Index: 140

Text #8

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1542710 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1583187 (Python Code)

Max Activating Token Index: 474

Text #10

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1427728 (Python Code)

Max Activating Token Index: 237

Text #11

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1406004 (Python Code)

Max Activating Token Index: 602

Text #12

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1528008 (Python Code)

Max Activating Token Index: 376

Text #13

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1594481 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1560484 (Python Code)

Max Activating Token Index: 250

Text #15

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1365263 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1544834 (Python Code)

Max Activating Token Index: 541

Text #17

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1650307 (Python Code)

Max Activating Token Index: 32

Text #18

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1503265 (Python Code)

Max Activating Token Index: 199

Text #19

Max Range: 0.9073. Min Range: -0.9073

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1624785 (Python Code)

Max Activating Token Index: 812