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

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

Neuron 3465 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: 2.3148. Min Range: -2.3148

Max Act: 2.3148. Min Act: -0.0001

Data Index: 1553674 (Python Code)

Max Activating Token Index: 794

Text #1

Max Range: 2.3148. Min Range: -2.3148

Max Act: 2.0470. Min Act: -0.0000

Data Index: 1374927 (Python Code)

Max Activating Token Index: 289

Text #2

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.9141. Min Act: -0.0000

Data Index: 1595670 (Python Code)

Max Activating Token Index: 192

Text #3

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.9953. Min Act: -0.0000

Data Index: 1526397 (Python Code)

Max Activating Token Index: 271

Text #4

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.9367. Min Act: -0.0000

Data Index: 1644413 (Python Code)

Max Activating Token Index: 129

Text #5

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.9566. Min Act: -0.0000

Data Index: 1603143 (Python Code)

Max Activating Token Index: 298

Text #6

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.7175. Min Act: -0.0000

Data Index: 1606632 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.9126. Min Act: -0.0000

Data Index: 1477749 (Python Code)

Max Activating Token Index: 654

Text #8

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.7595. Min Act: -0.0000

Data Index: 1380599 (Python Code)

Max Activating Token Index: 125

Text #9

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.7072. Min Act: -0.0000

Data Index: 1482850 (Python Code)

Max Activating Token Index: 748

Text #10

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.5445. Min Act: -0.0000

Data Index: 1609742 (Python Code)

Max Activating Token Index: 874

Text #11

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.5454. Min Act: -0.0000

Data Index: 1631747 (Python Code)

Max Activating Token Index: 345

Text #12

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.6157. Min Act: -0.0000

Data Index: 1441797 (Python Code)

Max Activating Token Index: 297

Text #13

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.4963. Min Act: -0.0000

Data Index: 1379865 (Python Code)

Max Activating Token Index: 629

Text #14

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.5802. Min Act: -0.0000

Data Index: 1408788 (Python Code)

Max Activating Token Index: 394

Text #15

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.5196. Min Act: -0.0000

Data Index: 1459567 (Python Code)

Max Activating Token Index: 828

Text #16

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.4787. Min Act: -0.0000

Data Index: 1421274 (Python Code)

Max Activating Token Index: 247

Text #17

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1564816 (Python Code)

Max Activating Token Index: 224

Text #18

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.5170. Min Act: -0.0000

Data Index: 1420041 (Python Code)

Max Activating Token Index: 524

Text #19

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1413128 (Python Code)

Max Activating Token Index: 492