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

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

Neuron 3998 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1366789 (Python Code)

Max Activating Token Index: 693

Text #1

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.2079. Min Act: -0.0000

Data Index: 856011 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1581098 (Python Code)

Max Activating Token Index: 883

Text #3

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1586850 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1539878 (Python Code)

Max Activating Token Index: 94

Text #5

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.2261. Min Act: -0.0000

Data Index: 1479054 (Python Code)

Max Activating Token Index: 269

Text #6

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1589224 (Python Code)

Max Activating Token Index: 517

Text #7

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.1434. Min Act: -0.0000

Data Index: 2350 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.2327. Min Range: -1.2327

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1639939 (Python Code)

Max Activating Token Index: 896

Text #9

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1550810 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1554139 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1391133 (Python Code)

Max Activating Token Index: 703

Text #12

Max Range: 1.2327. Min Range: -1.2327

Max Act: 1.0040. Min Act: -0.0000

Data Index: 272392 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.2327. Min Range: -1.2327

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1588724 (Python Code)

Max Activating Token Index: 946

Text #14

Max Range: 1.2327. Min Range: -1.2327

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1610385 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 1.2327. Min Range: -1.2327

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1364017 (Python Code)

Max Activating Token Index: 495

Text #16

Max Range: 1.2327. Min Range: -1.2327

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1405177 (Python Code)

Max Activating Token Index: 238

Text #17

Max Range: 1.2327. Min Range: -1.2327

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1648700 (Python Code)

Max Activating Token Index: 219

Text #18

Max Range: 1.2327. Min Range: -1.2327

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1595195 (Python Code)

Max Activating Token Index: 947

Text #19

Max Range: 1.2327. Min Range: -1.2327

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1463926 (Python Code)

Max Activating Token Index: 490