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

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

Neuron 1014 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.6539. Min Act: -0.0000

Data Index: 1533251 (Python Code)

Max Activating Token Index: 679

Text #1

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.6129. Min Act: -0.0000

Data Index: 1592163 (Python Code)

Max Activating Token Index: 977

Text #2

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.3250. Min Act: -0.0000

Data Index: 1435611 (Python Code)

Max Activating Token Index: 884

Text #3

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.5344. Min Act: -0.0000

Data Index: 1454690 (Python Code)

Max Activating Token Index: 994

Text #4

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.5199. Min Act: -0.0000

Data Index: 1601309 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.5125. Min Act: -0.0000

Data Index: 1473989 (Python Code)

Max Activating Token Index: 759

Text #6

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.4138. Min Act: -0.0000

Data Index: 1479847 (Python Code)

Max Activating Token Index: 497

Text #7

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.2955. Min Act: -0.0000

Data Index: 1458905 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.2013. Min Act: -0.0000

Data Index: 1405871 (Python Code)

Max Activating Token Index: 880

Text #9

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.2542. Min Act: -0.0000

Data Index: 1537154 (Python Code)

Max Activating Token Index: 550

Text #10

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.2224. Min Act: -0.0000

Data Index: 1586967 (Python Code)

Max Activating Token Index: 780

Text #11

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.2447. Min Act: -0.0000

Data Index: 1410206 (Python Code)

Max Activating Token Index: 384

Text #12

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.2605. Min Act: -0.0000

Data Index: 1518575 (Python Code)

Max Activating Token Index: 743

Text #13

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.0947. Min Act: -0.0000

Data Index: 1554280 (Python Code)

Max Activating Token Index: 965

Text #14

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.2098. Min Act: -0.0000

Data Index: 1423914 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.3784. Min Act: -0.0000

Data Index: 1506880 (Python Code)

Max Activating Token Index: 770

Text #16

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.0640. Min Act: -0.0000

Data Index: 1552536 (Python Code)

Max Activating Token Index: 346

Text #17

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.2149. Min Act: -0.0000

Data Index: 1638555 (Python Code)

Max Activating Token Index: 370

Text #18

Max Range: 3.6539. Min Range: -3.6539

Max Act: 3.2321. Min Act: -0.0000

Data Index: 1561699 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 3.6539. Min Range: -3.6539

Max Act: 2.8976. Min Act: -0.0000

Data Index: 1360698 (Python Code)

Max Activating Token Index: 1021