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

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

Neuron 4872 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2726. Min Range: -2.2726

Max Act: 2.1929. Min Act: -0.0000

Data Index: 1652432 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 2.2726. Min Range: -2.2726

Max Act: 2.2726. Min Act: -0.0000

Data Index: 1466149 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 2.2726. Min Range: -2.2726

Max Act: 2.0901. Min Act: -0.0000

Data Index: 1572455 (Python Code)

Max Activating Token Index: 548

Text #3

Max Range: 2.2726. Min Range: -2.2726

Max Act: 2.0632. Min Act: -0.0000

Data Index: 1412602 (Python Code)

Max Activating Token Index: 425

Text #4

Max Range: 2.2726. Min Range: -2.2726

Max Act: 2.0520. Min Act: -0.0000

Data Index: 1575638 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.8749. Min Act: -0.0000

Data Index: 1365465 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.9119. Min Act: -0.0000

Data Index: 1562837 (Python Code)

Max Activating Token Index: 256

Text #7

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.8878. Min Act: -0.0000

Data Index: 1635396 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.9797. Min Act: -0.0000

Data Index: 1517607 (Python Code)

Max Activating Token Index: 59

Text #9

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.8739. Min Act: -0.0000

Data Index: 1599192 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.7366. Min Act: -0.0000

Data Index: 1556471 (Python Code)

Max Activating Token Index: 176

Text #11

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.7382. Min Act: -0.0000

Data Index: 1372248 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.6801. Min Act: -0.0000

Data Index: 1574137 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.7591. Min Act: -0.0000

Data Index: 1540358 (Python Code)

Max Activating Token Index: 242

Text #14

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.5398. Min Act: -0.0000

Data Index: 1603763 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.6246. Min Act: -0.0000

Data Index: 1587585 (Python Code)

Max Activating Token Index: 132

Text #16

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.7876. Min Act: -0.0000

Data Index: 1622189 (Python Code)

Max Activating Token Index: 218

Text #17

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.7755. Min Act: -0.0000

Data Index: 1615035 (Python Code)

Max Activating Token Index: 391

Text #18

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.5687. Min Act: -0.0000

Data Index: 1414904 (Python Code)

Max Activating Token Index: 463

Text #19

Max Range: 2.2726. Min Range: -2.2726

Max Act: 1.7391. Min Act: -0.0000

Data Index: 1431898 (Python Code)

Max Activating Token Index: 76