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

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

Neuron 1015 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.7051. Min Act: -0.1700

Data Index: 1101082 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.7051. Min Act: -0.1700

Data Index: 642596 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.6894. Min Act: -0.1700

Data Index: 1231450 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.6581. Min Act: -0.1700

Data Index: 254557 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.5329. Min Act: -0.1700

Data Index: 89485 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.5172. Min Act: -0.1700

Data Index: 392498 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.4702. Min Act: -0.1700

Data Index: 820014 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.4859. Min Act: -0.1700

Data Index: 153057 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.4859. Min Act: -0.1700

Data Index: 803486 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.4702. Min Act: -0.1700

Data Index: 463516 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.4702. Min Act: -0.1700

Data Index: 756753 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.4702. Min Act: -0.1700

Data Index: 1189980 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.4232. Min Act: -0.1700

Data Index: 114875 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.3761. Min Act: -0.1700

Data Index: 1165931 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.3918. Min Act: -0.1700

Data Index: 403856 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.3918. Min Act: -0.1700

Data Index: 197249 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.3918. Min Act: -0.1700

Data Index: 477262 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.3918. Min Act: -0.1700

Data Index: 1130577 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.3761. Min Act: -0.1700

Data Index: 146951 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 3.7051. Min Range: -3.7051

Max Act: 3.3604. Min Act: -0.1700

Data Index: 240799 (C4 (Web Text))

Max Activating Token Index: 772