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

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

Neuron 4203 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3885. Min Range: -4.3885

Max Act: 4.2512. Min Act: -0.0000

Data Index: 1517898 (Python Code)

Max Activating Token Index: 739

Text #1

Max Range: 4.3885. Min Range: -4.3885

Max Act: 4.3885. Min Act: -0.0000

Data Index: 1634514 (Python Code)

Max Activating Token Index: 850

Text #2

Max Range: 4.3885. Min Range: -4.3885

Max Act: 4.2007. Min Act: -0.0000

Data Index: 1476038 (Python Code)

Max Activating Token Index: 413

Text #3

Max Range: 4.3885. Min Range: -4.3885

Max Act: 4.3585. Min Act: -0.0000

Data Index: 1361475 (Python Code)

Max Activating Token Index: 481

Text #4

Max Range: 4.3885. Min Range: -4.3885

Max Act: 4.0916. Min Act: -0.0000

Data Index: 1439169 (Python Code)

Max Activating Token Index: 489

Text #5

Max Range: 4.3885. Min Range: -4.3885

Max Act: 4.0669. Min Act: -0.0000

Data Index: 1469842 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.8731. Min Act: -0.0000

Data Index: 1444962 (Python Code)

Max Activating Token Index: 324

Text #7

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.8773. Min Act: -0.0000

Data Index: 1396100 (Python Code)

Max Activating Token Index: 789

Text #8

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.6215. Min Act: -0.0000

Data Index: 1581700 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.7691. Min Act: -0.0000

Data Index: 1388852 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.5948. Min Act: -0.0000

Data Index: 1545597 (Python Code)

Max Activating Token Index: 57

Text #11

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.4392. Min Act: -0.0000

Data Index: 1415557 (Python Code)

Max Activating Token Index: 921

Text #12

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.3979. Min Act: -0.0000

Data Index: 1561017 (Python Code)

Max Activating Token Index: 359

Text #13

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.5654. Min Act: -0.0000

Data Index: 1410150 (Python Code)

Max Activating Token Index: 95

Text #14

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.3594. Min Act: -0.0000

Data Index: 1419440 (Python Code)

Max Activating Token Index: 263

Text #15

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.2718. Min Act: -0.0000

Data Index: 1600359 (Python Code)

Max Activating Token Index: 498

Text #16

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.2133. Min Act: -0.0000

Data Index: 1603000 (Python Code)

Max Activating Token Index: 792

Text #17

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.1573. Min Act: -0.0000

Data Index: 1366108 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.1416. Min Act: -0.0000

Data Index: 1429280 (Python Code)

Max Activating Token Index: 74

Text #19

Max Range: 4.3885. Min Range: -4.3885

Max Act: 3.1190. Min Act: -0.0000

Data Index: 1510792 (Python Code)

Max Activating Token Index: 992