Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 394 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.8545. Min Act: -0.1700

Data Index: 1572553 (Python Code)

Max Activating Token Index: 289

Text #1

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.8232. Min Act: -0.1700

Data Index: 1457134 (Python Code)

Max Activating Token Index: 747

Text #2

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.8232. Min Act: -0.1700

Data Index: 1544561 (Python Code)

Max Activating Token Index: 732

Text #3

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.7920. Min Act: -0.1700

Data Index: 1633008 (Python Code)

Max Activating Token Index: 967

Text #4

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.7295. Min Act: -0.1700

Data Index: 509439 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.7295. Min Act: -0.1700

Data Index: 608657 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.7295. Min Act: -0.1700

Data Index: 1443919 (Python Code)

Max Activating Token Index: 210

Text #7

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6357. Min Act: -0.1700

Data Index: 1463691 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6982. Min Act: -0.1700

Data Index: 1590779 (Python Code)

Max Activating Token Index: 247

Text #9

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6670. Min Act: -0.1700

Data Index: 1461551 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6045. Min Act: -0.1700

Data Index: 1610720 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6670. Min Act: -0.1700

Data Index: 1377300 (Python Code)

Max Activating Token Index: 742

Text #12

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6045. Min Act: -0.1700

Data Index: 1444566 (Python Code)

Max Activating Token Index: 583

Text #13

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.5420. Min Act: -0.1700

Data Index: 1534744 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.7295. Min Act: -0.1700

Data Index: 1502577 (Python Code)

Max Activating Token Index: 445

Text #15

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6982. Min Act: -0.1700

Data Index: 448880 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6670. Min Act: -0.1700

Data Index: 606738 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6670. Min Act: -0.1700

Data Index: 1242695 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6045. Min Act: -0.1700

Data Index: 782979 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 5.8545. Min Range: -5.8545

Max Act: 5.6357. Min Act: -0.1700

Data Index: 1437755 (Python Code)

Max Activating Token Index: 636