Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 47 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.7486. Min Act: -0.1700

Data Index: 574209 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.5020. Min Act: -0.1700

Data Index: 797171 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.4260. Min Act: -0.1700

Data Index: 362436 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.4230. Min Act: -0.1700

Data Index: 1038743 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.3652. Min Act: -0.1700

Data Index: 43627 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.3010. Min Act: -0.1700

Data Index: 738957 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2604. Min Act: -0.1700

Data Index: 627496 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2402. Min Act: -0.1700

Data Index: 898030 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2413. Min Act: -0.1700

Data Index: 647187 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2335. Min Act: -0.1700

Data Index: 302798 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2207. Min Act: -0.1700

Data Index: 978053 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2060. Min Act: -0.1700

Data Index: 1605707 (Python Code)

Max Activating Token Index: 599

Text #12

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2060. Min Act: -0.1700

Data Index: 1387068 (Python Code)

Max Activating Token Index: 506

Text #13

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2291. Min Act: -0.1700

Data Index: 334909 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2033. Min Act: -0.1700

Data Index: 1265120 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1621. Min Act: -0.1700

Data Index: 823477 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2042. Min Act: -0.1700

Data Index: 759448 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1560. Min Act: -0.1700

Data Index: 987475 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1610. Min Act: -0.1700

Data Index: 1054802 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1323. Min Act: -0.1700

Data Index: 884371 (C4 (Web Text))

Max Activating Token Index: 733