Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 850 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1493434 (Python Code)

Max Activating Token Index: 439

Text #1

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1449921 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2210. Min Act: -0.0001

Data Index: 1630297 (Python Code)

Max Activating Token Index: 815

Text #3

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2185. Min Act: -0.0001

Data Index: 1487917 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2165. Min Act: -0.0001

Data Index: 1574464 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1437810 (Python Code)

Max Activating Token Index: 303

Text #6

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1434308 (Python Code)

Max Activating Token Index: 727

Text #7

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1411657 (Python Code)

Max Activating Token Index: 101

Text #8

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1643049 (Python Code)

Max Activating Token Index: 293

Text #9

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1652646 (Python Code)

Max Activating Token Index: 381

Text #10

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1440857 (Python Code)

Max Activating Token Index: 178

Text #11

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1402015 (Python Code)

Max Activating Token Index: 130

Text #12

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1639628 (Python Code)

Max Activating Token Index: 656

Text #13

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1361568 (Python Code)

Max Activating Token Index: 693

Text #14

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1422307 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1410022 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1568134 (Python Code)

Max Activating Token Index: 222

Text #17

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1755. Min Act: -0.0001

Data Index: 1612323 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1463402 (Python Code)

Max Activating Token Index: 632

Text #19

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1583. Min Act: -0.0000

Data Index: 1415337 (Python Code)

Max Activating Token Index: 964