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

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

Neuron 1441 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: 3.2825. Min Range: -3.2825

Max Act: 2.9685. Min Act: -0.0000

Data Index: 1494996 (Python Code)

Max Activating Token Index: 460

Text #1

Max Range: 3.2825. Min Range: -3.2825

Max Act: 3.2825. Min Act: -0.0000

Data Index: 1516079 (Python Code)

Max Activating Token Index: 751

Text #2

Max Range: 3.2825. Min Range: -3.2825

Max Act: 3.0665. Min Act: -0.0000

Data Index: 1436459 (Python Code)

Max Activating Token Index: 468

Text #3

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.9509. Min Act: -0.0000

Data Index: 1470850 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.5900. Min Act: 0.0000

Data Index: 1637848 (Python Code)

Max Activating Token Index: 299

Text #5

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.5591. Min Act: 0.0000

Data Index: 1596956 (Python Code)

Max Activating Token Index: 329

Text #6

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.5411. Min Act: -0.0000

Data Index: 1430853 (Python Code)

Max Activating Token Index: 69

Text #7

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.3993. Min Act: 0.0000

Data Index: 1440755 (Python Code)

Max Activating Token Index: 584

Text #8

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.4438. Min Act: -0.0000

Data Index: 1532055 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.1762. Min Act: -0.0000

Data Index: 1541875 (Python Code)

Max Activating Token Index: 925

Text #10

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.3836. Min Act: -0.0000

Data Index: 1461683 (Python Code)

Max Activating Token Index: 338

Text #11

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.2082. Min Act: -0.0000

Data Index: 1591893 (Python Code)

Max Activating Token Index: 266

Text #12

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.0153. Min Act: 0.0000

Data Index: 1407914 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 3.2825. Min Range: -3.2825

Max Act: 1.9818. Min Act: 0.0000

Data Index: 1467148 (Python Code)

Max Activating Token Index: 917

Text #14

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.0746. Min Act: 0.0000

Data Index: 1650971 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 3.2825. Min Range: -3.2825

Max Act: 1.9488. Min Act: -0.0000

Data Index: 1553548 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.0522. Min Act: 0.0000

Data Index: 1623592 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 3.2825. Min Range: -3.2825

Max Act: 2.0033. Min Act: -0.0000

Data Index: 1436157 (Python Code)

Max Activating Token Index: 151

Text #18

Max Range: 3.2825. Min Range: -3.2825

Max Act: 1.9235. Min Act: 0.0000

Data Index: 1585549 (Python Code)

Max Activating Token Index: 782

Text #19

Max Range: 3.2825. Min Range: -3.2825

Max Act: 1.9847. Min Act: 0.0000

Data Index: 1440427 (Python Code)

Max Activating Token Index: 415