Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2734 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1513659 (Python Code)

Max Activating Token Index: 384

Text #1

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1601409 (Python Code)

Max Activating Token Index: 287

Text #2

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1565825 (Python Code)

Max Activating Token Index: 978

Text #3

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1565534 (Python Code)

Max Activating Token Index: 437

Text #4

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1544556 (Python Code)

Max Activating Token Index: 725

Text #5

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1498071 (Python Code)

Max Activating Token Index: 603

Text #6

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1584378 (Python Code)

Max Activating Token Index: 499

Text #7

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1531048 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1555116 (Python Code)

Max Activating Token Index: 847

Text #9

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1545915 (Python Code)

Max Activating Token Index: 998

Text #10

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1433307 (Python Code)

Max Activating Token Index: 182

Text #11

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1438626 (Python Code)

Max Activating Token Index: 269

Text #12

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1482850 (Python Code)

Max Activating Token Index: 496

Text #13

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1555657 (Python Code)

Max Activating Token Index: 353

Text #14

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1508540 (Python Code)

Max Activating Token Index: 119

Text #15

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1558705 (Python Code)

Max Activating Token Index: 894

Text #16

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1451987 (Python Code)

Max Activating Token Index: 76

Text #17

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1600683 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1485529 (Python Code)

Max Activating Token Index: 993

Text #19

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1592740 (Python Code)

Max Activating Token Index: 659