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

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

Neuron 3538 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: 4.5129. Min Range: -4.5129

Max Act: 4.3437. Min Act: -0.0000

Data Index: 1458350 (Python Code)

Max Activating Token Index: 513

Text #1

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.5129. Min Act: -0.0000

Data Index: 1583031 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 4.5129. Min Range: -4.5129

Max Act: 4.0735. Min Act: -0.0000

Data Index: 1579508 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.8757. Min Act: -0.0000

Data Index: 1510570 (Python Code)

Max Activating Token Index: 652

Text #4

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.7794. Min Act: -0.0000

Data Index: 1604414 (Python Code)

Max Activating Token Index: 144

Text #5

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.5906. Min Act: -0.0000

Data Index: 1613175 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.5707. Min Act: -0.0000

Data Index: 1498398 (Python Code)

Max Activating Token Index: 1022

Text #7

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.5818. Min Act: -0.0000

Data Index: 1408500 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.4146. Min Act: -0.0000

Data Index: 1625553 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.5565. Min Act: -0.0000

Data Index: 1470835 (Python Code)

Max Activating Token Index: 166

Text #10

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.5220. Min Act: -0.0000

Data Index: 1614131 (Python Code)

Max Activating Token Index: 417

Text #11

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.4913. Min Act: -0.0000

Data Index: 1523769 (Python Code)

Max Activating Token Index: 820

Text #12

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.4843. Min Act: -0.0000

Data Index: 1398912 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.4659. Min Act: -0.0000

Data Index: 1624751 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.2888. Min Act: -0.0000

Data Index: 1559119 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.4436. Min Act: -0.0000

Data Index: 1450953 (Python Code)

Max Activating Token Index: 126

Text #16

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.5684. Min Act: -0.0000

Data Index: 1390319 (Python Code)

Max Activating Token Index: 340

Text #17

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.4369. Min Act: -0.0000

Data Index: 1486574 (Python Code)

Max Activating Token Index: 666

Text #18

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.4085. Min Act: -0.0000

Data Index: 1377758 (Python Code)

Max Activating Token Index: 577

Text #19

Max Range: 4.5129. Min Range: -4.5129

Max Act: 3.7053. Min Act: -0.0000

Data Index: 1626465 (Python Code)

Max Activating Token Index: 924