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

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

Neuron 2127 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: 3.0054. Min Range: -3.0054

Max Act: 3.0054. Min Act: -0.0000

Data Index: 1498510 (Python Code)

Max Activating Token Index: 423

Text #1

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.9630. Min Act: -0.0000

Data Index: 1608498 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.7162. Min Act: -0.0000

Data Index: 1403668 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.8811. Min Act: -0.0000

Data Index: 597644 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.6751. Min Act: -0.0000

Data Index: 1371193 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.4269. Min Act: -0.0000

Data Index: 1580917 (Python Code)

Max Activating Token Index: 237

Text #6

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.4095. Min Act: -0.0000

Data Index: 1642265 (Python Code)

Max Activating Token Index: 808

Text #7

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.4066. Min Act: -0.0000

Data Index: 1511141 (Python Code)

Max Activating Token Index: 519

Text #8

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.2528. Min Act: -0.0000

Data Index: 1522692 (Python Code)

Max Activating Token Index: 760

Text #9

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.3446. Min Act: -0.0000

Data Index: 1392459 (Python Code)

Max Activating Token Index: 172

Text #10

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.2816. Min Act: -0.0000

Data Index: 1550414 (Python Code)

Max Activating Token Index: 76

Text #11

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.3816. Min Act: -0.0000

Data Index: 1501060 (Python Code)

Max Activating Token Index: 344

Text #12

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.3796. Min Act: -0.0000

Data Index: 1578974 (Python Code)

Max Activating Token Index: 313

Text #13

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.2474. Min Act: -0.0000

Data Index: 1523683 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.2352. Min Act: -0.0000

Data Index: 1513548 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.1193. Min Act: -0.0000

Data Index: 361521 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.0005. Min Act: -0.0000

Data Index: 1398183 (Python Code)

Max Activating Token Index: 186

Text #17

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.0942. Min Act: -0.0000

Data Index: 1457611 (Python Code)

Max Activating Token Index: 36

Text #18

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.3404. Min Act: -0.0000

Data Index: 1560162 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 3.0054. Min Range: -3.0054

Max Act: 2.1851. Min Act: -0.0000

Data Index: 1604369 (Python Code)

Max Activating Token Index: 197