Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1277 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.9465. Min Act: -0.1700

Data Index: 820083 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.9152. Min Act: -0.1700

Data Index: 1304684 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.7588. Min Act: -0.1700

Data Index: 805728 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6963. Min Act: -0.1700

Data Index: 597765 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6963. Min Act: -0.1700

Data Index: 19895 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6650. Min Act: -0.1700

Data Index: 644603 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6650. Min Act: -0.1700

Data Index: 599048 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6650. Min Act: -0.1700

Data Index: 203760 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6337. Min Act: -0.1700

Data Index: 206026 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6023. Min Act: -0.1700

Data Index: 990555 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.5710. Min Act: -0.1700

Data Index: 591705 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6023. Min Act: -0.1700

Data Index: 310728 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.5710. Min Act: -0.1700

Data Index: 491788 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6023. Min Act: -0.1700

Data Index: 1111013 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.5710. Min Act: -0.1700

Data Index: 1217741 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6023. Min Act: -0.1700

Data Index: 493661 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6023. Min Act: -0.1700

Data Index: 1334000 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6023. Min Act: -0.1700

Data Index: 1127736 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6023. Min Act: -0.1700

Data Index: 1047401 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.5710. Min Act: -0.1700

Data Index: 727047 (C4 (Web Text))

Max Activating Token Index: 975