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

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

Neuron 1098 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: 5.8426. Min Range: -5.8426

Max Act: 5.8426. Min Act: -0.1700

Data Index: 1197665 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.7176. Min Act: -0.1700

Data Index: 499160 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.8114. Min Act: -0.1700

Data Index: 110454 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.6551. Min Act: -0.1700

Data Index: 796663 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.6239. Min Act: -0.1700

Data Index: 1224623 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.5458. Min Act: -0.1700

Data Index: 508135 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.4989. Min Act: -0.1700

Data Index: 1362680 (Python Code)

Max Activating Token Index: 701

Text #7

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.5145. Min Act: -0.1700

Data Index: 60643 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.4676. Min Act: -0.1700

Data Index: 63542 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.5301. Min Act: -0.1700

Data Index: 234429 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.5301. Min Act: -0.1700

Data Index: 1644707 (Python Code)

Max Activating Token Index: 860

Text #11

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.4833. Min Act: -0.1700

Data Index: 1044350 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.4520. Min Act: -0.1700

Data Index: 990905 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.4208. Min Act: -0.1700

Data Index: 446183 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.3895. Min Act: -0.1700

Data Index: 644701 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.4208. Min Act: -0.1700

Data Index: 993483 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.4051. Min Act: -0.1700

Data Index: 1593 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.3895. Min Act: -0.1700

Data Index: 801676 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.3739. Min Act: -0.1700

Data Index: 344766 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 5.8426. Min Range: -5.8426

Max Act: 5.3583. Min Act: -0.1700

Data Index: 1117672 (C4 (Web Text))

Max Activating Token Index: 878