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

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

Neuron 1130 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.2340. Min Act: -0.1700

Data Index: 623285 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.1553. Min Act: -0.1700

Data Index: 1169898 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.1238. Min Act: -0.1700

Data Index: 1332552 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.1238. Min Act: -0.1700

Data Index: 862219 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.1081. Min Act: -0.1700

Data Index: 1063501 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.1081. Min Act: -0.1700

Data Index: 172737 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0765. Min Act: -0.1700

Data Index: 1296796 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0765. Min Act: -0.1700

Data Index: 211544 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0607. Min Act: -0.1700

Data Index: 560526 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0765. Min Act: -0.1700

Data Index: 810281 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0607. Min Act: -0.1700

Data Index: 941345 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0765. Min Act: -0.1700

Data Index: 272575 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0449. Min Act: -0.1700

Data Index: 663846 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0449. Min Act: -0.1700

Data Index: 404704 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0292. Min Act: -0.1700

Data Index: 393770 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0449. Min Act: -0.1700

Data Index: 635990 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0292. Min Act: -0.1700

Data Index: 709404 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0292. Min Act: -0.1700

Data Index: 790364 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0292. Min Act: -0.1700

Data Index: 11485 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 3.2340. Min Range: -3.2340

Max Act: 3.0292. Min Act: -0.1700

Data Index: 859862 (C4 (Web Text))

Max Activating Token Index: 586