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

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

Neuron 3322 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1613524 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1551663 (Python Code)

Max Activating Token Index: 41

Text #2

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1514792 (Python Code)

Max Activating Token Index: 226

Text #3

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1369849 (Python Code)

Max Activating Token Index: 350

Text #4

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1420352 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1564563 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1522058 (Python Code)

Max Activating Token Index: 736

Text #7

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1399333 (Python Code)

Max Activating Token Index: 307

Text #8

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1637341 (Python Code)

Max Activating Token Index: 183

Text #9

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1484520 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1536173 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1378648 (Python Code)

Max Activating Token Index: 530

Text #12

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1360557 (Python Code)

Max Activating Token Index: 404

Text #13

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1501098 (Python Code)

Max Activating Token Index: 193

Text #14

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1558330 (Python Code)

Max Activating Token Index: 470

Text #15

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1499585 (Python Code)

Max Activating Token Index: 277

Text #16

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1618451 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1527014 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.5994. Min Act: -0.0001

Data Index: 1608967 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 0.8024. Min Range: -0.8024

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1523292 (Python Code)

Max Activating Token Index: 905