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

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

Neuron 2183 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5665. Min Range: -3.5665

Max Act: 3.5665. Min Act: -0.0000

Data Index: 1601037 (Python Code)

Max Activating Token Index: 418

Text #1

Max Range: 3.5665. Min Range: -3.5665

Max Act: 3.2274. Min Act: -0.0000

Data Index: 1410106 (Python Code)

Max Activating Token Index: 821

Text #2

Max Range: 3.5665. Min Range: -3.5665

Max Act: 3.1921. Min Act: -0.0000

Data Index: 1618989 (Python Code)

Max Activating Token Index: 841

Text #3

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.9500. Min Act: -0.0000

Data Index: 1597866 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.9335. Min Act: -0.0000

Data Index: 1493121 (Python Code)

Max Activating Token Index: 416

Text #5

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.9114. Min Act: -0.0000

Data Index: 1392126 (Python Code)

Max Activating Token Index: 1011

Text #6

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.9414. Min Act: -0.0000

Data Index: 1372527 (Python Code)

Max Activating Token Index: 639

Text #7

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.8755. Min Act: -0.0000

Data Index: 1368220 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.9020. Min Act: -0.0000

Data Index: 1615093 (Python Code)

Max Activating Token Index: 458

Text #9

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.9113. Min Act: -0.0000

Data Index: 1356228 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.8777. Min Act: -0.0000

Data Index: 1562285 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.6801. Min Act: -0.0000

Data Index: 1639670 (Python Code)

Max Activating Token Index: 444

Text #12

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.8418. Min Act: -0.0000

Data Index: 1533042 (Python Code)

Max Activating Token Index: 1012

Text #13

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.8496. Min Act: -0.0000

Data Index: 1491045 (Python Code)

Max Activating Token Index: 787

Text #14

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.8508. Min Act: -0.0000

Data Index: 1632837 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.9663. Min Act: -0.0000

Data Index: 1646107 (Python Code)

Max Activating Token Index: 294

Text #16

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.8399. Min Act: -0.0000

Data Index: 1649759 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.8262. Min Act: -0.0000

Data Index: 1364789 (Python Code)

Max Activating Token Index: 421

Text #18

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.6476. Min Act: -0.0000

Data Index: 471472 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 3.5665. Min Range: -3.5665

Max Act: 2.7744. Min Act: -0.0000

Data Index: 1551899 (Python Code)

Max Activating Token Index: 650