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

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

Neuron 633 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.4708. Min Act: -0.1700

Data Index: 888937 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3453. Min Act: -0.1700

Data Index: 41391 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.4081. Min Act: -0.1700

Data Index: 72232 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3767. Min Act: -0.1700

Data Index: 828117 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3767. Min Act: -0.1700

Data Index: 1439831 (Python Code)

Max Activating Token Index: 240

Text #5

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3767. Min Act: -0.1700

Data Index: 1649955 (Python Code)

Max Activating Token Index: 827

Text #6

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3453. Min Act: -0.1700

Data Index: 400246 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3767. Min Act: -0.1700

Data Index: 1069787 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3139. Min Act: -0.1700

Data Index: 263523 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3453. Min Act: -0.1700

Data Index: 1592707 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3767. Min Act: -0.1700

Data Index: 1524438 (Python Code)

Max Activating Token Index: 590

Text #11

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3139. Min Act: -0.1700

Data Index: 543200 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3139. Min Act: -0.1700

Data Index: 311514 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3453. Min Act: -0.1700

Data Index: 588734 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.3139. Min Act: -0.1700

Data Index: 983201 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.2825. Min Act: -0.1700

Data Index: 1387741 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.2511. Min Act: -0.1700

Data Index: 1495330 (Python Code)

Max Activating Token Index: 671

Text #17

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.2825. Min Act: -0.1700

Data Index: 1519430 (Python Code)

Max Activating Token Index: 587

Text #18

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.2825. Min Act: -0.1700

Data Index: 1551514 (Python Code)

Max Activating Token Index: 215

Text #19

Max Range: 3.4708. Min Range: -3.4708

Max Act: 3.2825. Min Act: -0.1700

Data Index: 697508 (C4 (Web Text))

Max Activating Token Index: 813