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

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

Neuron 116 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: 3.2562. Min Range: -3.2562

Max Act: 3.2562. Min Act: -0.1700

Data Index: 980665 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.2562. Min Range: -3.2562

Max Act: 3.2248. Min Act: -0.1700

Data Index: 473925 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.2562. Min Range: -3.2562

Max Act: 3.0988. Min Act: -0.1700

Data Index: 507308 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 3.2562. Min Range: -3.2562

Max Act: 3.0988. Min Act: -0.1700

Data Index: 273783 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 3.2562. Min Range: -3.2562

Max Act: 3.1303. Min Act: -0.1700

Data Index: 973925 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.2562. Min Range: -3.2562

Max Act: 3.0672. Min Act: -0.1700

Data Index: 860968 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 3.2562. Min Range: -3.2562

Max Act: 3.0988. Min Act: -0.1700

Data Index: 425592 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.2562. Min Range: -3.2562

Max Act: 3.0357. Min Act: -0.1700

Data Index: 300313 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.9724. Min Act: -0.1700

Data Index: 1334302 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.9724. Min Act: -0.1700

Data Index: 413330 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.9724. Min Act: -0.1700

Data Index: 271000 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.9724. Min Act: -0.1700

Data Index: 468985 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.9724. Min Act: -0.1700

Data Index: 56838 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 3.2562. Min Range: -3.2562

Max Act: 3.0041. Min Act: -0.1700

Data Index: 316434 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.9724. Min Act: -0.1700

Data Index: 909374 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.9408. Min Act: -0.1700

Data Index: 307302 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.9408. Min Act: -0.1700

Data Index: 655364 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.9724. Min Act: -0.1700

Data Index: 988654 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.9408. Min Act: -0.1700

Data Index: 763048 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 3.2562. Min Range: -3.2562

Max Act: 2.8774. Min Act: -0.1700

Data Index: 1252656 (C4 (Web Text))

Max Activating Token Index: 670