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

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

Neuron 3682 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: 4.2058. Min Range: -4.2058

Max Act: 3.7863. Min Act: -0.0000

Data Index: 1648735 (Python Code)

Max Activating Token Index: 355

Text #1

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.2058. Min Act: -0.0000

Data Index: 1499003 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 4.2058. Min Range: -4.2058

Max Act: 3.9489. Min Act: -0.0000

Data Index: 1594802 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 4.2058. Min Range: -4.2058

Max Act: 3.0350. Min Act: -0.0000

Data Index: 1542671 (Python Code)

Max Activating Token Index: 898

Text #4

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.8805. Min Act: -0.0000

Data Index: 1540098 (Python Code)

Max Activating Token Index: 976

Text #5

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.8326. Min Act: -0.0000

Data Index: 1652648 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.7366. Min Act: -0.0000

Data Index: 1552692 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.8800. Min Act: -0.0000

Data Index: 1560752 (Python Code)

Max Activating Token Index: 855

Text #8

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.5961. Min Act: -0.0000

Data Index: 1646868 (Python Code)

Max Activating Token Index: 471

Text #9

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.5825. Min Act: -0.0000

Data Index: 1656768 (Python Code)

Max Activating Token Index: 443

Text #10

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.6850. Min Act: -0.0000

Data Index: 1381280 (Python Code)

Max Activating Token Index: 440

Text #11

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.5099. Min Act: -0.0000

Data Index: 1502805 (Python Code)

Max Activating Token Index: 1012

Text #12

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.7729. Min Act: -0.0000

Data Index: 1453309 (Python Code)

Max Activating Token Index: 783

Text #13

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.6470. Min Act: -0.0000

Data Index: 1475095 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.4997. Min Act: -0.0000

Data Index: 1650681 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.4671. Min Act: -0.0000

Data Index: 1597499 (Python Code)

Max Activating Token Index: 850

Text #16

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.6275. Min Act: -0.0000

Data Index: 1616723 (Python Code)

Max Activating Token Index: 823

Text #17

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.5680. Min Act: -0.0000

Data Index: 1446449 (Python Code)

Max Activating Token Index: 345

Text #18

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.5507. Min Act: -0.0000

Data Index: 1398572 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 4.2058. Min Range: -4.2058

Max Act: 2.5847. Min Act: -0.0000

Data Index: 1529514 (Python Code)

Max Activating Token Index: 831