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

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

Neuron 4283 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: 0.1870. Min Range: -0.1870

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1627689 (Python Code)

Max Activating Token Index: 472

Text #1

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1771. Min Act: -0.0000

Data Index: 33634 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1700. Min Act: -0.0000

Data Index: 74986 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1352417 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1525. Min Act: -0.0000

Data Index: 379739 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1425. Min Act: -0.0000

Data Index: 248988 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1421. Min Act: -0.0000

Data Index: 145466 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1047236 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1497. Min Act: -0.0000

Data Index: 1179762 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1530. Min Act: -0.0000

Data Index: 420757 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1483410 (Python Code)

Max Activating Token Index: 875

Text #11

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1293. Min Act: -0.0000

Data Index: 420319 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1572087 (Python Code)

Max Activating Token Index: 566

Text #13

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1327. Min Act: -0.0000

Data Index: 601225 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1279750 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1235. Min Act: -0.0000

Data Index: 50551 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1219. Min Act: -0.0000

Data Index: 853795 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1159. Min Act: -0.0000

Data Index: 721806 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1196. Min Act: -0.0000

Data Index: 954117 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1522725 (Python Code)

Max Activating Token Index: 558