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

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

Neuron 4719 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8045. Min Range: -2.8045

Max Act: 2.8045. Min Act: -0.0000

Data Index: 1195257 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 2.8045. Min Range: -2.8045

Max Act: 2.4412. Min Act: -0.0000

Data Index: 86132 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 2.8045. Min Range: -2.8045

Max Act: 2.2409. Min Act: -0.0000

Data Index: 301599 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 2.8045. Min Range: -2.8045

Max Act: 2.2278. Min Act: -0.0000

Data Index: 960433 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 2.8045. Min Range: -2.8045

Max Act: 2.0347. Min Act: -0.0000

Data Index: 1608203 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 2.8045. Min Range: -2.8045

Max Act: 2.0337. Min Act: -0.0000

Data Index: 1478236 (Python Code)

Max Activating Token Index: 169

Text #6

Max Range: 2.8045. Min Range: -2.8045

Max Act: 2.0004. Min Act: -0.0000

Data Index: 16392 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 2.8045. Min Range: -2.8045

Max Act: 1.9854. Min Act: -0.0000

Data Index: 1608851 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 2.8045. Min Range: -2.8045

Max Act: 2.0809. Min Act: -0.0000

Data Index: 1478398 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 2.8045. Min Range: -2.8045

Max Act: 1.9720. Min Act: -0.0000

Data Index: 1474928 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 2.8045. Min Range: -2.8045

Max Act: 1.8889. Min Act: -0.0000

Data Index: 1454065 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 2.8045. Min Range: -2.8045

Max Act: 2.0559. Min Act: -0.0000

Data Index: 1327795 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 2.8045. Min Range: -2.8045

Max Act: 2.0260. Min Act: -0.0000

Data Index: 110864 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 2.8045. Min Range: -2.8045

Max Act: 1.8992. Min Act: -0.0000

Data Index: 1553222 (Python Code)

Max Activating Token Index: 794

Text #14

Max Range: 2.8045. Min Range: -2.8045

Max Act: 1.9575. Min Act: -0.0000

Data Index: 1555633 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 2.8045. Min Range: -2.8045

Max Act: 1.9278. Min Act: -0.0000

Data Index: 1425084 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 2.8045. Min Range: -2.8045

Max Act: 1.9234. Min Act: -0.0000

Data Index: 1580067 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 2.8045. Min Range: -2.8045

Max Act: 1.7955. Min Act: -0.0000

Data Index: 1646964 (Python Code)

Max Activating Token Index: 290

Text #18

Max Range: 2.8045. Min Range: -2.8045

Max Act: 1.7607. Min Act: -0.0000

Data Index: 1441839 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 2.8045. Min Range: -2.8045

Max Act: 1.6689. Min Act: -0.0000

Data Index: 293798 (C4 (Web Text))

Max Activating Token Index: 257