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

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

Neuron 1941 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: 3.7992. Min Range: -3.7992

Max Act: 3.7992. Min Act: -0.1700

Data Index: 1421984 (Python Code)

Max Activating Token Index: 423

Text #1

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.7053. Min Act: -0.1700

Data Index: 1619103 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.7053. Min Act: -0.1700

Data Index: 1635999 (Python Code)

Max Activating Token Index: 593

Text #3

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.6897. Min Act: -0.1699

Data Index: 1483855 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.6584. Min Act: -0.1700

Data Index: 1420638 (Python Code)

Max Activating Token Index: 405

Text #5

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.6584. Min Act: -0.1700

Data Index: 1447505 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.6427. Min Act: -0.1700

Data Index: 1481306 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.6271. Min Act: -0.1700

Data Index: 1417720 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.6114. Min Act: -0.1700

Data Index: 1580330 (Python Code)

Max Activating Token Index: 1003

Text #9

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.6271. Min Act: -0.1700

Data Index: 1497203 (Python Code)

Max Activating Token Index: 286

Text #10

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.6427. Min Act: -0.1700

Data Index: 1384976 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.6114. Min Act: -0.1700

Data Index: 1472867 (Python Code)

Max Activating Token Index: 290

Text #12

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.6271. Min Act: -0.1700

Data Index: 1400684 (Python Code)

Max Activating Token Index: 122

Text #13

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.5801. Min Act: -0.1700

Data Index: 1447773 (Python Code)

Max Activating Token Index: 255

Text #14

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.5957. Min Act: -0.1700

Data Index: 1552325 (Python Code)

Max Activating Token Index: 445

Text #15

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.5957. Min Act: -0.1700

Data Index: 1617578 (Python Code)

Max Activating Token Index: 942

Text #16

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.5801. Min Act: -0.1700

Data Index: 1543909 (Python Code)

Max Activating Token Index: 469

Text #17

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.5957. Min Act: -0.1700

Data Index: 1431971 (Python Code)

Max Activating Token Index: 589

Text #18

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.5957. Min Act: -0.1700

Data Index: 1513421 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 3.7992. Min Range: -3.7992

Max Act: 3.5957. Min Act: -0.1700

Data Index: 1366251 (Python Code)

Max Activating Token Index: 424