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

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

Neuron 5538 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3531. Min Range: -2.3531

Max Act: 2.3531. Min Act: -0.0000

Data Index: 11877 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 2.3531. Min Range: -2.3531

Max Act: 2.0041. Min Act: -0.0000

Data Index: 855373 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 2.3531. Min Range: -2.3531

Max Act: 1.5213. Min Act: -0.0000

Data Index: 482407 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 2.3531. Min Range: -2.3531

Max Act: 1.4050. Min Act: -0.0000

Data Index: 632934 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 2.3531. Min Range: -2.3531

Max Act: 1.2747. Min Act: -0.0000

Data Index: 1574876 (Python Code)

Max Activating Token Index: 845

Text #5

Max Range: 2.3531. Min Range: -2.3531

Max Act: 1.2000. Min Act: -0.0000

Data Index: 73602 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 2.3531. Min Range: -2.3531

Max Act: 1.2311. Min Act: -0.0000

Data Index: 1454478 (Python Code)

Max Activating Token Index: 877

Text #7

Max Range: 2.3531. Min Range: -2.3531

Max Act: 1.2506. Min Act: -0.0000

Data Index: 1442823 (Python Code)

Max Activating Token Index: 938

Text #8

Max Range: 2.3531. Min Range: -2.3531

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1475144 (Python Code)

Max Activating Token Index: 516

Text #9

Max Range: 2.3531. Min Range: -2.3531

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1477416 (Python Code)

Max Activating Token Index: 614

Text #10

Max Range: 2.3531. Min Range: -2.3531

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1430431 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 2.3531. Min Range: -2.3531

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1625427 (Python Code)

Max Activating Token Index: 453

Text #12

Max Range: 2.3531. Min Range: -2.3531

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1592301 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 2.3531. Min Range: -2.3531

Max Act: 0.8936. Min Act: -0.0000

Data Index: 1491392 (Python Code)

Max Activating Token Index: 621

Text #14

Max Range: 2.3531. Min Range: -2.3531

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1453821 (Python Code)

Max Activating Token Index: 690

Text #15

Max Range: 2.3531. Min Range: -2.3531

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1430260 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 2.3531. Min Range: -2.3531

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1093009 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 2.3531. Min Range: -2.3531

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1507144 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 2.3531. Min Range: -2.3531

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1582532 (Python Code)

Max Activating Token Index: 735

Text #19

Max Range: 2.3531. Min Range: -2.3531

Max Act: 0.8459. Min Act: -0.0000

Data Index: 455165 (C4 (Web Text))

Max Activating Token Index: 262