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

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

Neuron 277 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: 3.7218. Min Range: -3.7218

Max Act: 3.7218. Min Act: -0.1700

Data Index: 1494156 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5965. Min Act: -0.1700

Data Index: 1491000 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5026. Min Act: -0.1700

Data Index: 1590269 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3928. Min Act: -0.1700

Data Index: 1421085 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3928. Min Act: -0.1700

Data Index: 1440375 (Python Code)

Max Activating Token Index: 793

Text #5

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3615. Min Act: -0.1700

Data Index: 1501334 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3615. Min Act: -0.1700

Data Index: 1481762 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3301. Min Act: -0.1700

Data Index: 1536526 (Python Code)

Max Activating Token Index: 405

Text #8

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3301. Min Act: -0.1700

Data Index: 1508531 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3458. Min Act: -0.1700

Data Index: 1556728 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3458. Min Act: -0.1700

Data Index: 1421080 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3458. Min Act: -0.1700

Data Index: 1372623 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3458. Min Act: -0.1700

Data Index: 1521903 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3301. Min Act: -0.1700

Data Index: 1429919 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3458. Min Act: -0.1700

Data Index: 1417380 (Python Code)

Max Activating Token Index: 794

Text #15

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3458. Min Act: -0.1700

Data Index: 1532451 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3301. Min Act: -0.1700

Data Index: 1459127 (Python Code)

Max Activating Token Index: 450

Text #17

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3301. Min Act: -0.1700

Data Index: 1361848 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3144. Min Act: -0.1700

Data Index: 1485251 (Python Code)

Max Activating Token Index: 437

Text #19

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.3144. Min Act: -0.1700

Data Index: 1431257 (Python Code)

Max Activating Token Index: 6