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

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

Neuron 3078 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.9006. Min Act: -0.0001

Data Index: 904050 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.8301. Min Act: -0.0001

Data Index: 589808 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.7628. Min Act: -0.0000

Data Index: 759558 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.8637. Min Act: -0.0000

Data Index: 1366675 (Python Code)

Max Activating Token Index: 68

Text #4

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.7110. Min Act: -0.0001

Data Index: 1026746 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.5725. Min Act: -0.0000

Data Index: 482301 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.8494. Min Act: -0.0001

Data Index: 1647060 (Python Code)

Max Activating Token Index: 180

Text #7

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.8042. Min Act: -0.0000

Data Index: 1446331 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.5682. Min Act: -0.0000

Data Index: 1481079 (Python Code)

Max Activating Token Index: 722

Text #9

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.6266. Min Act: -0.0000

Data Index: 1405429 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.6246. Min Act: -0.0001

Data Index: 1496815 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.4403. Min Act: -0.0000

Data Index: 348230 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.5807. Min Act: -0.0001

Data Index: 928104 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.4993. Min Act: -0.0000

Data Index: 1023589 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.5548. Min Act: -0.0000

Data Index: 1489873 (Python Code)

Max Activating Token Index: 136

Text #15

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.5354. Min Act: -0.0001

Data Index: 1457174 (Python Code)

Max Activating Token Index: 302

Text #16

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.6884. Min Act: -0.0001

Data Index: 1174175 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.4262. Min Act: -0.0001

Data Index: 1194120 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.4366. Min Act: -0.0001

Data Index: 380369 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.9006. Min Range: -1.9006

Max Act: 1.3937. Min Act: -0.0001

Data Index: 1496070 (Python Code)

Max Activating Token Index: 920