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

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

Neuron 313 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7298. Min Range: -1.7298

Max Act: 1.7298. Min Act: -0.0000

Data Index: 1508049 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 1.7298. Min Range: -1.7298

Max Act: 1.4641. Min Act: -0.0000

Data Index: 1634399 (Python Code)

Max Activating Token Index: 315

Text #2

Max Range: 1.7298. Min Range: -1.7298

Max Act: 1.3077. Min Act: -0.0000

Data Index: 1598913 (Python Code)

Max Activating Token Index: 124

Text #3

Max Range: 1.7298. Min Range: -1.7298

Max Act: 1.2290. Min Act: -0.0000

Data Index: 1478006 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 1.7298. Min Range: -1.7298

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1412237 (Python Code)

Max Activating Token Index: 559

Text #5

Max Range: 1.7298. Min Range: -1.7298

Max Act: 1.1294. Min Act: -0.0000

Data Index: 229327 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1550595 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.9427. Min Act: -0.0000

Data Index: 859576 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1432487 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1641433 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1633281 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1248502 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1607589 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1420974 (Python Code)

Max Activating Token Index: 208

Text #14

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1457191 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1395903 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.8742. Min Act: -0.0000

Data Index: 963816 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1493271 (Python Code)

Max Activating Token Index: 126

Text #18

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.8950. Min Act: -0.0000

Data Index: 209720 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 1.7298. Min Range: -1.7298

Max Act: 0.8701. Min Act: -0.0000

Data Index: 671784 (C4 (Web Text))

Max Activating Token Index: 72