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

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

Neuron 3044 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.8159. Min Act: -0.0000

Data Index: 525540 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7941. Min Act: -0.0000

Data Index: 997034 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1475751 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1407329 (Python Code)

Max Activating Token Index: 883

Text #4

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6922. Min Act: -0.0000

Data Index: 11972 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1370292 (Python Code)

Max Activating Token Index: 902

Text #6

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1583246 (Python Code)

Max Activating Token Index: 551

Text #7

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6424. Min Act: -0.0000

Data Index: 809728 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1611220 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1645878 (Python Code)

Max Activating Token Index: 417

Text #10

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1198684 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6335. Min Act: -0.0000

Data Index: 548336 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1474544 (Python Code)

Max Activating Token Index: 923

Text #13

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1410787 (Python Code)

Max Activating Token Index: 809

Text #14

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1364170 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1094828 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5756. Min Act: -0.0000

Data Index: 698332 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1434530 (Python Code)

Max Activating Token Index: 324

Text #18

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1521165 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1080778 (C4 (Web Text))

Max Activating Token Index: 587