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

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

Neuron 1427 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5607. Min Act: -0.1700

Data Index: 858414 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.6546. Min Act: -0.1700

Data Index: 420060 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5607. Min Act: -0.1700

Data Index: 642338 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5607. Min Act: -0.1700

Data Index: 932074 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5294. Min Act: -0.1700

Data Index: 71456 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5294. Min Act: -0.1700

Data Index: 734075 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5294. Min Act: -0.1700

Data Index: 184365 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5294. Min Act: -0.1700

Data Index: 402775 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.4980. Min Act: -0.1700

Data Index: 175386 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.4667. Min Act: -0.1700

Data Index: 674513 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5294. Min Act: -0.1700

Data Index: 531806 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5294. Min Act: -0.1700

Data Index: 870689 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5294. Min Act: -0.1700

Data Index: 481304 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.4980. Min Act: -0.1700

Data Index: 711594 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.4353. Min Act: -0.1700

Data Index: 57035 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5294. Min Act: -0.1700

Data Index: 1027332 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.4980. Min Act: -0.1700

Data Index: 880678 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.5294. Min Act: -0.1700

Data Index: 844512 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.4040. Min Act: -0.1700

Data Index: 563469 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 3.6546. Min Range: -3.6546

Max Act: 3.4040. Min Act: -0.1700

Data Index: 757091 (C4 (Web Text))

Max Activating Token Index: 459