Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1857 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.3615. Min Act: -0.1700

Data Index: 1571269 (Python Code)

Max Activating Token Index: 427

Text #1

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.1257. Min Act: -0.1700

Data Index: 1557784 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.1415. Min Act: -0.1700

Data Index: 1562203 (Python Code)

Max Activating Token Index: 736

Text #3

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.1415. Min Act: -0.1700

Data Index: 1647754 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.1257. Min Act: -0.1700

Data Index: 1593637 (Python Code)

Max Activating Token Index: 889

Text #5

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.1100. Min Act: -0.1700

Data Index: 1406423 (Python Code)

Max Activating Token Index: 335

Text #6

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.1100. Min Act: -0.1700

Data Index: 1575405 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.1100. Min Act: -0.1700

Data Index: 1488573 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0784. Min Act: -0.1700

Data Index: 1380050 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0784. Min Act: -0.1700

Data Index: 1493516 (Python Code)

Max Activating Token Index: 593

Text #10

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0784. Min Act: -0.1700

Data Index: 1494762 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0784. Min Act: -0.1700

Data Index: 1585131 (Python Code)

Max Activating Token Index: 706

Text #12

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0784. Min Act: -0.1700

Data Index: 1642751 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0784. Min Act: -0.1700

Data Index: 1642891 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0626. Min Act: -0.1700

Data Index: 1558492 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0626. Min Act: -0.1700

Data Index: 1469416 (Python Code)

Max Activating Token Index: 538

Text #16

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0626. Min Act: -0.1700

Data Index: 1428976 (Python Code)

Max Activating Token Index: 405

Text #17

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0469. Min Act: -0.1700

Data Index: 1644955 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0626. Min Act: -0.1700

Data Index: 1470030 (Python Code)

Max Activating Token Index: 923

Text #19

Max Range: 3.3615. Min Range: -3.3615

Max Act: 3.0469. Min Act: -0.1700

Data Index: 1437050 (Python Code)

Max Activating Token Index: 624