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

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

Neuron 2417 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1862. Min Range: -6.1862

Max Act: 6.1862. Min Act: -0.0000

Data Index: 1410104 (Python Code)

Max Activating Token Index: 94

Text #1

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.8326. Min Act: -0.0000

Data Index: 1499956 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.7457. Min Act: -0.0000

Data Index: 1400293 (Python Code)

Max Activating Token Index: 767

Text #3

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.1366. Min Act: -0.0001

Data Index: 1384479 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.6679. Min Act: -0.0000

Data Index: 1378915 (Python Code)

Max Activating Token Index: 461

Text #5

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.4755. Min Act: -0.0000

Data Index: 1521839 (Python Code)

Max Activating Token Index: 971

Text #6

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.5162. Min Act: -0.0000

Data Index: 1445951 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.5083. Min Act: -0.0000

Data Index: 1604443 (Python Code)

Max Activating Token Index: 330

Text #8

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.7069. Min Act: -0.0000

Data Index: 1494002 (Python Code)

Max Activating Token Index: 689

Text #9

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.3403. Min Act: -0.0000

Data Index: 1369114 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.1856. Min Act: -0.0000

Data Index: 1406927 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.5035. Min Act: -0.0000

Data Index: 1562827 (Python Code)

Max Activating Token Index: 861

Text #12

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.4754. Min Act: -0.0000

Data Index: 1468673 (Python Code)

Max Activating Token Index: 474

Text #13

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.3077. Min Act: -0.0000

Data Index: 1463617 (Python Code)

Max Activating Token Index: 122

Text #14

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.2989. Min Act: -0.0001

Data Index: 1472462 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.4595. Min Act: -0.0000

Data Index: 1589983 (Python Code)

Max Activating Token Index: 996

Text #16

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.4425. Min Act: -0.0000

Data Index: 1568860 (Python Code)

Max Activating Token Index: 80

Text #17

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.4554. Min Act: -0.0000

Data Index: 1498572 (Python Code)

Max Activating Token Index: 405

Text #18

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.4324. Min Act: -0.0000

Data Index: 1434126 (Python Code)

Max Activating Token Index: 370

Text #19

Max Range: 6.1862. Min Range: -6.1862

Max Act: 5.4449. Min Act: -0.0000

Data Index: 1587636 (Python Code)

Max Activating Token Index: 416