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

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

Neuron 1315 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6628. Min Act: -0.1700

Data Index: 1442454 (Python Code)

Max Activating Token Index: 906

Text #1

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6628. Min Act: -0.1700

Data Index: 1522269 (Python Code)

Max Activating Token Index: 553

Text #2

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6472. Min Act: -0.1700

Data Index: 1552031 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.6159. Min Act: -0.1700

Data Index: 1422672 (Python Code)

Max Activating Token Index: 556

Text #4

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1404571 (Python Code)

Max Activating Token Index: 325

Text #5

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1626917 (Python Code)

Max Activating Token Index: 839

Text #6

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1590929 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5845. Min Act: -0.1700

Data Index: 1456435 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5532. Min Act: -0.1700

Data Index: 1470413 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5376. Min Act: -0.1700

Data Index: 1517932 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5845. Min Act: -0.1700

Data Index: 1567616 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5532. Min Act: -0.1700

Data Index: 1427752 (Python Code)

Max Activating Token Index: 941

Text #12

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1590046 (Python Code)

Max Activating Token Index: 929

Text #13

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5062. Min Act: -0.1700

Data Index: 1476859 (Python Code)

Max Activating Token Index: 774

Text #14

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5219. Min Act: -0.1700

Data Index: 1365331 (Python Code)

Max Activating Token Index: 103

Text #15

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.4906. Min Act: -0.1700

Data Index: 1395257 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5062. Min Act: -0.1700

Data Index: 1414346 (Python Code)

Max Activating Token Index: 762

Text #17

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5062. Min Act: -0.1700

Data Index: 1374245 (Python Code)

Max Activating Token Index: 361

Text #18

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.5219. Min Act: -0.1700

Data Index: 1360763 (Python Code)

Max Activating Token Index: 490

Text #19

Max Range: 3.6628. Min Range: -3.6628

Max Act: 3.4592. Min Act: -0.1700

Data Index: 1463341 (Python Code)

Max Activating Token Index: 302