Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 810 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.8611. Min Act: -0.1700

Data Index: 435474 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.7360. Min Act: -0.1700

Data Index: 1106536 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.7360. Min Act: -0.1700

Data Index: 223687 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.7047. Min Act: -0.1700

Data Index: 1339920 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.7047. Min Act: -0.1700

Data Index: 459976 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6264. Min Act: -0.1700

Data Index: 881304 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6264. Min Act: -0.1700

Data Index: 1064618 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6108. Min Act: -0.1700

Data Index: 1503658 (Python Code)

Max Activating Token Index: 120

Text #8

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6108. Min Act: -0.1700

Data Index: 1186479 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.5638. Min Act: -0.1700

Data Index: 972293 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.5638. Min Act: -0.1700

Data Index: 1176556 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.5638. Min Act: -0.1700

Data Index: 217698 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.4855. Min Act: -0.1700

Data Index: 360368 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.4855. Min Act: -0.1700

Data Index: 537805 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.4855. Min Act: -0.1700

Data Index: 694229 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.4855. Min Act: -0.1700

Data Index: 571180 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.4384. Min Act: -0.1700

Data Index: 454764 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.4384. Min Act: -0.1700

Data Index: 957172 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.4541. Min Act: -0.1700

Data Index: 1123956 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.4228. Min Act: -0.1700

Data Index: 5523 (C4 (Web Text))

Max Activating Token Index: 382