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

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

Neuron 545 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.3611. Min Act: -0.1700

Data Index: 1147635 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.3297. Min Act: -0.1700

Data Index: 314355 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.2669. Min Act: -0.1700

Data Index: 85799 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.2040. Min Act: -0.1700

Data Index: 1341140 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.2040. Min Act: -0.1700

Data Index: 1314105 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1883. Min Act: -0.1700

Data Index: 1123155 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1411. Min Act: -0.1700

Data Index: 942978 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1726. Min Act: -0.1700

Data Index: 15159 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1883. Min Act: -0.1700

Data Index: 546309 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1568. Min Act: -0.1700

Data Index: 85660 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1095. Min Act: -0.1700

Data Index: 1137772 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1253. Min Act: -0.1700

Data Index: 889070 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1253. Min Act: -0.1700

Data Index: 1181056 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1253. Min Act: -0.1700

Data Index: 1152377 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1726. Min Act: -0.1700

Data Index: 684304 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.0938. Min Act: -0.1700

Data Index: 1000142 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1253. Min Act: -0.1700

Data Index: 933756 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.0780. Min Act: -0.1700

Data Index: 1341657 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.0938. Min Act: -0.1700

Data Index: 1246669 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 3.3611. Min Range: -3.3611

Max Act: 3.1095. Min Act: -0.1700

Data Index: 401429 (C4 (Web Text))

Max Activating Token Index: 966