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

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

Neuron 853 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: 1.0134. Min Range: -1.0134

Max Act: 1.0134. Min Act: -0.0000

Data Index: 949746 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1516509 (Python Code)

Max Activating Token Index: 1006

Text #2

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1621036 (Python Code)

Max Activating Token Index: 674

Text #3

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.9235. Min Act: -0.0000

Data Index: 755125 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1428810 (Python Code)

Max Activating Token Index: 520

Text #5

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8553. Min Act: -0.0000

Data Index: 638906 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8286. Min Act: -0.0000

Data Index: 822573 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8121. Min Act: -0.0000

Data Index: 182711 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1395409 (Python Code)

Max Activating Token Index: 779

Text #9

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7728. Min Act: -0.0000

Data Index: 845115 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1492361 (Python Code)

Max Activating Token Index: 332

Text #11

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1402016 (Python Code)

Max Activating Token Index: 1020

Text #12

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1553324 (Python Code)

Max Activating Token Index: 662

Text #13

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1549324 (Python Code)

Max Activating Token Index: 864

Text #14

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7563. Min Act: -0.0000

Data Index: 28039 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1417521 (Python Code)

Max Activating Token Index: 324

Text #16

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7717. Min Act: -0.0000

Data Index: 229183 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1462515 (Python Code)

Max Activating Token Index: 568

Text #18

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1544061 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 1.0134. Min Range: -1.0134

Max Act: 0.7522. Min Act: -0.0000

Data Index: 83835 (C4 (Web Text))

Max Activating Token Index: 884