Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 476 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.1625. Min Act: -0.1700

Data Index: 928170 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.1312. Min Act: -0.1700

Data Index: 1345988 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.1312. Min Act: -0.1700

Data Index: 807191 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.1000. Min Act: -0.1700

Data Index: 381945 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.0687. Min Act: -0.1700

Data Index: 1273025 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.0375. Min Act: -0.1700

Data Index: 228888 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.0062. Min Act: -0.1700

Data Index: 964200 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.0375. Min Act: -0.1700

Data Index: 1054938 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.0062. Min Act: -0.1700

Data Index: 1256143 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.0375. Min Act: -0.1700

Data Index: 758262 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.0375. Min Act: -0.1700

Data Index: 910508 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 5.1625. Min Range: -5.1625

Max Act: 4.9750. Min Act: -0.1700

Data Index: 1016667 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 5.1625. Min Range: -5.1625

Max Act: 5.0062. Min Act: -0.1700

Data Index: 586128 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 5.1625. Min Range: -5.1625

Max Act: 4.9750. Min Act: -0.1700

Data Index: 905324 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 5.1625. Min Range: -5.1625

Max Act: 4.9437. Min Act: -0.1700

Data Index: 711516 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 5.1625. Min Range: -5.1625

Max Act: 4.9750. Min Act: -0.1700

Data Index: 486987 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 5.1625. Min Range: -5.1625

Max Act: 4.9750. Min Act: -0.1700

Data Index: 466499 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 5.1625. Min Range: -5.1625

Max Act: 4.9437. Min Act: -0.1700

Data Index: 831965 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 5.1625. Min Range: -5.1625

Max Act: 4.9750. Min Act: -0.1700

Data Index: 176179 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 5.1625. Min Range: -5.1625

Max Act: 4.9750. Min Act: -0.1700

Data Index: 796915 (C4 (Web Text))

Max Activating Token Index: 1011