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

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

Neuron 6065 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: 1.7435. Min Range: -1.7435

Max Act: 1.7435. Min Act: -0.0000

Data Index: 1400379 (Python Code)

Max Activating Token Index: 855

Text #1

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.3847. Min Act: -0.0000

Data Index: 1645950 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1588778 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1465563 (Python Code)

Max Activating Token Index: 880

Text #4

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.2626. Min Act: -0.0000

Data Index: 1382306 (Python Code)

Max Activating Token Index: 749

Text #5

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1474052 (Python Code)

Max Activating Token Index: 516

Text #6

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1530461 (Python Code)

Max Activating Token Index: 765

Text #7

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.0395. Min Act: -0.0000

Data Index: 874467 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1487236 (Python Code)

Max Activating Token Index: 813

Text #9

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1367106 (Python Code)

Max Activating Token Index: 477

Text #10

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1649768 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1490904 (Python Code)

Max Activating Token Index: 276

Text #12

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1546326 (Python Code)

Max Activating Token Index: 691

Text #13

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1482273 (Python Code)

Max Activating Token Index: 408

Text #14

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1501408 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1360934 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.8897. Min Act: -0.0000

Data Index: 1608706 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1485272 (Python Code)

Max Activating Token Index: 71

Text #18

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1412108 (Python Code)

Max Activating Token Index: 476

Text #19

Max Range: 1.7435. Min Range: -1.7435

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1578558 (Python Code)

Max Activating Token Index: 667