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

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

Neuron 939 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1422785 (Python Code)

Max Activating Token Index: 959

Text #1

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1432327 (Python Code)

Max Activating Token Index: 261

Text #2

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9261. Min Act: -0.0001

Data Index: 1595550 (Python Code)

Max Activating Token Index: 739

Text #3

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1463448 (Python Code)

Max Activating Token Index: 456

Text #4

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1623851 (Python Code)

Max Activating Token Index: 312

Text #5

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1365885 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1551521 (Python Code)

Max Activating Token Index: 425

Text #7

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1597855 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1402591 (Python Code)

Max Activating Token Index: 257

Text #9

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1424700 (Python Code)

Max Activating Token Index: 195

Text #10

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1654545 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1470118 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1473684 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1583882 (Python Code)

Max Activating Token Index: 126

Text #14

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1455281 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1639983 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1560195 (Python Code)

Max Activating Token Index: 222

Text #17

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1645176 (Python Code)

Max Activating Token Index: 127

Text #18

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1449157 (Python Code)

Max Activating Token Index: 401

Text #19

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1397158 (Python Code)

Max Activating Token Index: 456