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

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

Neuron 1712 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4262. Min Act: -0.0002

Data Index: 1526910 (Python Code)

Max Activating Token Index: 1012

Text #1

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4356. Min Act: -0.0002

Data Index: 1466191 (Python Code)

Max Activating Token Index: 307

Text #2

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3592. Min Act: -0.0002

Data Index: 1627424 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4362. Min Act: -0.0002

Data Index: 1481603 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4044. Min Act: -0.0002

Data Index: 1527830 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4552. Min Act: -0.0002

Data Index: 1371508 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3512. Min Act: -0.0002

Data Index: 1390405 (Python Code)

Max Activating Token Index: 210

Text #7

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3953. Min Act: -0.0002

Data Index: 1571368 (Python Code)

Max Activating Token Index: 221

Text #8

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3847. Min Act: -0.0002

Data Index: 1396387 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4054. Min Act: -0.0002

Data Index: 1453551 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3693. Min Act: -0.0002

Data Index: 1392027 (Python Code)

Max Activating Token Index: 310

Text #11

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4294. Min Act: -0.0002

Data Index: 1460748 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4215. Min Act: -0.0002

Data Index: 1400247 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3973. Min Act: -0.0002

Data Index: 1468165 (Python Code)

Max Activating Token Index: 522

Text #14

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4012. Min Act: -0.0002

Data Index: 1533924 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3986. Min Act: -0.0002

Data Index: 1546299 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3950. Min Act: -0.0002

Data Index: 1585233 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3699. Min Act: -0.0002

Data Index: 1466667 (Python Code)

Max Activating Token Index: 233

Text #18

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4167. Min Act: -0.0002

Data Index: 1651477 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3972. Min Act: -0.0002

Data Index: 1589787 (Python Code)

Max Activating Token Index: 265