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

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

Neuron 1108 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.7949. Min Act: -0.0000

Data Index: 1533325 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.8134. Min Act: -0.0000

Data Index: 1535810 (Python Code)

Max Activating Token Index: 694

Text #2

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.7153. Min Act: -0.0000

Data Index: 1551831 (Python Code)

Max Activating Token Index: 751

Text #3

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.5439. Min Act: -0.0000

Data Index: 1603642 (Python Code)

Max Activating Token Index: 444

Text #4

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1530594 (Python Code)

Max Activating Token Index: 826

Text #5

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.3047. Min Act: -0.0000

Data Index: 1369061 (Python Code)

Max Activating Token Index: 601

Text #6

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.3482. Min Act: -0.0000

Data Index: 1455826 (Python Code)

Max Activating Token Index: 594

Text #7

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.2489. Min Act: 0.0000

Data Index: 1609087 (Python Code)

Max Activating Token Index: 108

Text #8

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1418544 (Python Code)

Max Activating Token Index: 570

Text #9

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.1722. Min Act: -0.0000

Data Index: 912156 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.0701. Min Act: -0.0000

Data Index: 909667 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 1.8134. Min Range: -1.8134

Max Act: 0.9502. Min Act: -0.0000

Data Index: 753188 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 1.8134. Min Range: -1.8134

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1149590 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1653610 (Python Code)

Max Activating Token Index: 565

Text #14

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.0317. Min Act: -0.0000

Data Index: 987562 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 1.8134. Min Range: -1.8134

Max Act: 0.9825. Min Act: -0.0000

Data Index: 1380403 (Python Code)

Max Activating Token Index: 621

Text #16

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1371770 (Python Code)

Max Activating Token Index: 856

Text #17

Max Range: 1.8134. Min Range: -1.8134

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1584292 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 1.8134. Min Range: -1.8134

Max Act: 0.9608. Min Act: -0.0000

Data Index: 1300935 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1273849 (C4 (Web Text))

Max Activating Token Index: 454