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

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

Neuron 3198 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4116. Min Range: -2.4116

Max Act: 2.4116. Min Act: -0.0000

Data Index: 1598452 (Python Code)

Max Activating Token Index: 999

Text #1

Max Range: 2.4116. Min Range: -2.4116

Max Act: 2.1808. Min Act: -0.0000

Data Index: 1463854 (Python Code)

Max Activating Token Index: 993

Text #2

Max Range: 2.4116. Min Range: -2.4116

Max Act: 2.0014. Min Act: -0.0000

Data Index: 1591904 (Python Code)

Max Activating Token Index: 1016

Text #3

Max Range: 2.4116. Min Range: -2.4116

Max Act: 2.0998. Min Act: -0.0000

Data Index: 1440525 (Python Code)

Max Activating Token Index: 762

Text #4

Max Range: 2.4116. Min Range: -2.4116

Max Act: 2.1408. Min Act: -0.0000

Data Index: 1533971 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 2.4116. Min Range: -2.4116

Max Act: 2.0571. Min Act: -0.0000

Data Index: 1600417 (Python Code)

Max Activating Token Index: 331

Text #6

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.9933. Min Act: -0.0000

Data Index: 1477297 (Python Code)

Max Activating Token Index: 661

Text #7

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.9652. Min Act: -0.0000

Data Index: 253602 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.8481. Min Act: -0.0000

Data Index: 336399 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 2.4116. Min Range: -2.4116

Max Act: 2.0443. Min Act: -0.0000

Data Index: 1511648 (Python Code)

Max Activating Token Index: 1011

Text #10

Max Range: 2.4116. Min Range: -2.4116

Max Act: 2.0003. Min Act: -0.0000

Data Index: 1641393 (Python Code)

Max Activating Token Index: 713

Text #11

Max Range: 2.4116. Min Range: -2.4116

Max Act: 2.0949. Min Act: -0.0000

Data Index: 1589543 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.9172. Min Act: -0.0000

Data Index: 656933 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1531403 (Python Code)

Max Activating Token Index: 311

Text #14

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.8812. Min Act: -0.0000

Data Index: 1595837 (Python Code)

Max Activating Token Index: 692

Text #15

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.7238. Min Act: -0.0000

Data Index: 564436 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.7342. Min Act: -0.0000

Data Index: 1451690 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.9158. Min Act: -0.0000

Data Index: 1488348 (Python Code)

Max Activating Token Index: 741

Text #18

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.8373. Min Act: -0.0000

Data Index: 1443943 (Python Code)

Max Activating Token Index: 986

Text #19

Max Range: 2.4116. Min Range: -2.4116

Max Act: 1.7856. Min Act: -0.0000

Data Index: 1552031 (Python Code)

Max Activating Token Index: 993