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

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

Neuron 2034 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2320. Min Range: -4.2320

Max Act: 4.2320. Min Act: -0.1700

Data Index: 1649232 (Python Code)

Max Activating Token Index: 345

Text #1

Max Range: 4.2320. Min Range: -4.2320

Max Act: 4.2008. Min Act: -0.1700

Data Index: 1373097 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 4.2320. Min Range: -4.2320

Max Act: 4.0914. Min Act: -0.1700

Data Index: 1576773 (Python Code)

Max Activating Token Index: 522

Text #3

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.9976. Min Act: -0.1700

Data Index: 1507986 (Python Code)

Max Activating Token Index: 215

Text #4

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.9663. Min Act: -0.1700

Data Index: 1588646 (Python Code)

Max Activating Token Index: 350

Text #5

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.9663. Min Act: -0.1700

Data Index: 1550821 (Python Code)

Max Activating Token Index: 598

Text #6

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.9507. Min Act: -0.1700

Data Index: 344674 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.9350. Min Act: -0.1700

Data Index: 1504836 (Python Code)

Max Activating Token Index: 894

Text #8

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.9350. Min Act: -0.1700

Data Index: 1420457 (Python Code)

Max Activating Token Index: 686

Text #9

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.9507. Min Act: -0.1700

Data Index: 1514361 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.9038. Min Act: -0.1700

Data Index: 1548747 (Python Code)

Max Activating Token Index: 411

Text #11

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.8568. Min Act: -0.1700

Data Index: 1514241 (Python Code)

Max Activating Token Index: 658

Text #12

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.8881. Min Act: -0.1700

Data Index: 1557290 (Python Code)

Max Activating Token Index: 914

Text #13

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.8881. Min Act: -0.1700

Data Index: 1446970 (Python Code)

Max Activating Token Index: 1007

Text #14

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.8568. Min Act: -0.1700

Data Index: 1457687 (Python Code)

Max Activating Token Index: 598

Text #15

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.8412. Min Act: -0.1700

Data Index: 1527423 (Python Code)

Max Activating Token Index: 561

Text #16

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.8568. Min Act: -0.1700

Data Index: 1405578 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.8412. Min Act: -0.1700

Data Index: 1395914 (Python Code)

Max Activating Token Index: 470

Text #18

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.8725. Min Act: -0.1700

Data Index: 1502104 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 4.2320. Min Range: -4.2320

Max Act: 3.8412. Min Act: -0.1700

Data Index: 1563146 (Python Code)

Max Activating Token Index: 1013