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

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

Neuron 5543 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: 0.6167. Min Range: -0.6167

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1603183 (Python Code)

Max Activating Token Index: 204

Text #1

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1449289 (Python Code)

Max Activating Token Index: 757

Text #2

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1413188 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1375377 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1511345 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1527191 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1421166 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1599555 (Python Code)

Max Activating Token Index: 295

Text #8

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1489804 (Python Code)

Max Activating Token Index: 842

Text #9

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1588154 (Python Code)

Max Activating Token Index: 310

Text #10

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1633646 (Python Code)

Max Activating Token Index: 106

Text #11

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1545508 (Python Code)

Max Activating Token Index: 286

Text #12

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1491587 (Python Code)

Max Activating Token Index: 345

Text #13

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1478481 (Python Code)

Max Activating Token Index: 732

Text #14

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1577729 (Python Code)

Max Activating Token Index: 877

Text #15

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1495278 (Python Code)

Max Activating Token Index: 684

Text #16

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1449671 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1521195 (Python Code)

Max Activating Token Index: 747

Text #18

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1405320 (Python Code)

Max Activating Token Index: 837

Text #19

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1534620 (Python Code)

Max Activating Token Index: 547