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

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

Neuron 1822 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.8850. Min Act: -0.1700

Data Index: 174488 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.9787. Min Act: -0.1700

Data Index: 792931 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.7600. Min Act: -0.1700

Data Index: 715907 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6975. Min Act: -0.1700

Data Index: 106181 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6350. Min Act: -0.1700

Data Index: 959390 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6975. Min Act: -0.1700

Data Index: 641332 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.5725. Min Act: -0.1700

Data Index: 1352234 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6350. Min Act: -0.1700

Data Index: 1319741 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6037. Min Act: -0.1700

Data Index: 978392 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6350. Min Act: -0.1700

Data Index: 990661 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6350. Min Act: -0.1700

Data Index: 699415 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6037. Min Act: -0.1700

Data Index: 1129592 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.5100. Min Act: -0.1700

Data Index: 1214790 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.5100. Min Act: -0.1700

Data Index: 830467 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6037. Min Act: -0.1700

Data Index: 524105 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6350. Min Act: -0.1700

Data Index: 360547 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.5100. Min Act: -0.1700

Data Index: 1074524 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.5725. Min Act: -0.1700

Data Index: 1004148 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.5412. Min Act: -0.1700

Data Index: 480124 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 5.9787. Min Range: -5.9787

Max Act: 5.6037. Min Act: -0.1700

Data Index: 411636 (C4 (Web Text))

Max Activating Token Index: 472