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

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

Neuron 395 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0046. Min Range: -3.0046

Max Act: 3.0046. Min Act: -0.0001

Data Index: 1417214 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 3.0046. Min Range: -3.0046

Max Act: 2.5113. Min Act: -0.0001

Data Index: 1431318 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 3.0046. Min Range: -3.0046

Max Act: 2.3090. Min Act: -0.0001

Data Index: 1382933 (Python Code)

Max Activating Token Index: 627

Text #3

Max Range: 3.0046. Min Range: -3.0046

Max Act: 2.1670. Min Act: -0.0001

Data Index: 1460473 (Python Code)

Max Activating Token Index: 706

Text #4

Max Range: 3.0046. Min Range: -3.0046

Max Act: 2.3112. Min Act: -0.0000

Data Index: 1538303 (Python Code)

Max Activating Token Index: 398

Text #5

Max Range: 3.0046. Min Range: -3.0046

Max Act: 2.0822. Min Act: -0.0001

Data Index: 1309773 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 3.0046. Min Range: -3.0046

Max Act: 2.0047. Min Act: -0.0000

Data Index: 1575974 (Python Code)

Max Activating Token Index: 337

Text #7

Max Range: 3.0046. Min Range: -3.0046

Max Act: 2.1135. Min Act: -0.0000

Data Index: 570376 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 3.0046. Min Range: -3.0046

Max Act: 1.9781. Min Act: -0.0001

Data Index: 1513586 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 3.0046. Min Range: -3.0046

Max Act: 1.9533. Min Act: -0.0001

Data Index: 1408229 (Python Code)

Max Activating Token Index: 89

Text #10

Max Range: 3.0046. Min Range: -3.0046

Max Act: 2.0517. Min Act: -0.0000

Data Index: 1520832 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 3.0046. Min Range: -3.0046

Max Act: 2.0434. Min Act: -0.0001

Data Index: 1333505 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 3.0046. Min Range: -3.0046

Max Act: 2.0690. Min Act: -0.0001

Data Index: 420703 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 3.0046. Min Range: -3.0046

Max Act: 1.9846. Min Act: -0.0001

Data Index: 955255 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 3.0046. Min Range: -3.0046

Max Act: 1.8499. Min Act: -0.0000

Data Index: 1519231 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 3.0046. Min Range: -3.0046

Max Act: 1.6927. Min Act: -0.0001

Data Index: 361929 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 3.0046. Min Range: -3.0046

Max Act: 1.7324. Min Act: -0.0001

Data Index: 420189 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 3.0046. Min Range: -3.0046

Max Act: 1.8911. Min Act: -0.0001

Data Index: 1589691 (Python Code)

Max Activating Token Index: 324

Text #18

Max Range: 3.0046. Min Range: -3.0046

Max Act: 1.7058. Min Act: -0.0001

Data Index: 1099416 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 3.0046. Min Range: -3.0046

Max Act: 1.7886. Min Act: -0.0001

Data Index: 870361 (C4 (Web Text))

Max Activating Token Index: 889