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

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

Neuron 3406 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1286901 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1358209 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2791. Min Act: -0.0000

Data Index: 828840 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2614. Min Act: -0.0000

Data Index: 717171 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2533. Min Act: -0.0000

Data Index: 226702 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1329056 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2198. Min Act: -0.0000

Data Index: 419600 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1558894 (Python Code)

Max Activating Token Index: 532

Text #8

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2118. Min Act: -0.0000

Data Index: 672840 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1577835 (Python Code)

Max Activating Token Index: 1000

Text #10

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1145762 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2231. Min Act: -0.0000

Data Index: 440382 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1061638 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1273442 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1420215 (Python Code)

Max Activating Token Index: 891

Text #15

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.1913. Min Act: -0.0000

Data Index: 692200 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.1836. Min Act: -0.0000

Data Index: 324018 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1173973 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1290636 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.3240. Min Range: -0.3240

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1593723 (Python Code)

Max Activating Token Index: 498