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

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

Neuron 3688 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9663. Min Range: -4.9663

Max Act: 4.9663. Min Act: -0.0000

Data Index: 1616823 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.8209. Min Act: -0.0000

Data Index: 1591512 (Python Code)

Max Activating Token Index: 208

Text #2

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.6820. Min Act: -0.0000

Data Index: 1570406 (Python Code)

Max Activating Token Index: 229

Text #3

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.5778. Min Act: -0.0000

Data Index: 1549609 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.3519. Min Act: -0.0000

Data Index: 1618455 (Python Code)

Max Activating Token Index: 409

Text #5

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.4978. Min Act: -0.0000

Data Index: 1455247 (Python Code)

Max Activating Token Index: 371

Text #6

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.4408. Min Act: -0.0000

Data Index: 1370588 (Python Code)

Max Activating Token Index: 881

Text #7

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.3565. Min Act: -0.0000

Data Index: 329154 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.1936. Min Act: -0.0000

Data Index: 1548633 (Python Code)

Max Activating Token Index: 535

Text #9

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.2239. Min Act: -0.0000

Data Index: 1647302 (Python Code)

Max Activating Token Index: 828

Text #10

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.1327. Min Act: -0.0000

Data Index: 1465677 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.4397. Min Act: -0.0000

Data Index: 1380295 (Python Code)

Max Activating Token Index: 377

Text #12

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.0769. Min Act: -0.0000

Data Index: 1603380 (Python Code)

Max Activating Token Index: 607

Text #13

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.1931. Min Act: -0.0000

Data Index: 610116 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 4.9663. Min Range: -4.9663

Max Act: 3.2269. Min Act: -0.0000

Data Index: 1502788 (Python Code)

Max Activating Token Index: 955

Text #15

Max Range: 4.9663. Min Range: -4.9663

Max Act: 2.6911. Min Act: -0.0000

Data Index: 609578 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 4.9663. Min Range: -4.9663

Max Act: 2.7660. Min Act: -0.0000

Data Index: 1547285 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 4.9663. Min Range: -4.9663

Max Act: 2.6631. Min Act: -0.0000

Data Index: 451403 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 4.9663. Min Range: -4.9663

Max Act: 2.4929. Min Act: -0.0000

Data Index: 1281320 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 4.9663. Min Range: -4.9663

Max Act: 2.4537. Min Act: -0.0000

Data Index: 1419770 (Python Code)

Max Activating Token Index: 800