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

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

Neuron 2231 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3436. Min Act: -0.0000

Data Index: 690529 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3219. Min Act: -0.0000

Data Index: 140953 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3091. Min Act: -0.0000

Data Index: 316472 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2525. Min Act: -0.0000

Data Index: 194850 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1701. Min Act: -0.0000

Data Index: 262528 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1359744 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2397. Min Act: -0.0000

Data Index: 584350 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2272. Min Act: -0.0000

Data Index: 459594 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1126190 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1325556 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1377655 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2434. Min Act: -0.0000

Data Index: 676491 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2038. Min Act: -0.0000

Data Index: 732419 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2054. Min Act: -0.0000

Data Index: 525928 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2066. Min Act: -0.0000

Data Index: 45919 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1396167 (Python Code)

Max Activating Token Index: 331

Text #16

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1927. Min Act: -0.0000

Data Index: 223834 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1405458 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1249748 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2244. Min Act: -0.0000

Data Index: 241184 (C4 (Web Text))

Max Activating Token Index: 44