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

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

Neuron 4856 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6407. Min Range: -6.6407

Max Act: 6.6407. Min Act: -0.0000

Data Index: 1591373 (Python Code)

Max Activating Token Index: 726

Text #1

Max Range: 6.6407. Min Range: -6.6407

Max Act: 6.3260. Min Act: -0.0000

Data Index: 1416389 (Python Code)

Max Activating Token Index: 873

Text #2

Max Range: 6.6407. Min Range: -6.6407

Max Act: 6.4122. Min Act: -0.0000

Data Index: 1649381 (Python Code)

Max Activating Token Index: 96

Text #3

Max Range: 6.6407. Min Range: -6.6407

Max Act: 6.1573. Min Act: -0.0000

Data Index: 295314 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.6648. Min Act: -0.0000

Data Index: 1594402 (Python Code)

Max Activating Token Index: 721

Text #5

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.9567. Min Act: -0.0000

Data Index: 1579848 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.9134. Min Act: -0.0000

Data Index: 1434210 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.5129. Min Act: -0.0000

Data Index: 1481945 (Python Code)

Max Activating Token Index: 450

Text #8

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.6346. Min Act: -0.0000

Data Index: 1502613 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.6299. Min Act: -0.0000

Data Index: 1518421 (Python Code)

Max Activating Token Index: 971

Text #10

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.4073. Min Act: -0.0000

Data Index: 1385286 (Python Code)

Max Activating Token Index: 938

Text #11

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.4891. Min Act: -0.0000

Data Index: 1366304 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.9569. Min Act: -0.0001

Data Index: 1657008 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.7800. Min Act: -0.0000

Data Index: 1384746 (Python Code)

Max Activating Token Index: 44

Text #14

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.1733. Min Act: -0.0000

Data Index: 1103072 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.9512. Min Act: -0.0000

Data Index: 1467254 (Python Code)

Max Activating Token Index: 690

Text #16

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.2982. Min Act: -0.0000

Data Index: 804553 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.8012. Min Act: -0.0000

Data Index: 440808 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.3733. Min Act: -0.0000

Data Index: 1370389 (Python Code)

Max Activating Token Index: 98

Text #19

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.3301. Min Act: -0.0000

Data Index: 681044 (C4 (Web Text))

Max Activating Token Index: 41