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

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

Neuron 1349 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.7344. Min Act: -0.1700

Data Index: 1125768 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.6248. Min Act: -0.1700

Data Index: 249209 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.6092. Min Act: -0.1700

Data Index: 137609 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.5935. Min Act: -0.1700

Data Index: 640912 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.5465. Min Act: -0.1700

Data Index: 399671 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.5152. Min Act: -0.1700

Data Index: 1265320 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.5152. Min Act: -0.1700

Data Index: 1253184 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4995. Min Act: -0.1700

Data Index: 728471 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4995. Min Act: -0.1700

Data Index: 760957 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4995. Min Act: -0.1700

Data Index: 763403 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4839. Min Act: -0.1700

Data Index: 371541 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4995. Min Act: -0.1700

Data Index: 1086878 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4839. Min Act: -0.1700

Data Index: 1252442 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4682. Min Act: -0.1700

Data Index: 674084 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4839. Min Act: -0.1700

Data Index: 781923 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4682. Min Act: -0.1700

Data Index: 714133 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4682. Min Act: -0.1700

Data Index: 1319125 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4682. Min Act: -0.1700

Data Index: 557153 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4525. Min Act: -0.1700

Data Index: 125617 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 3.7344. Min Range: -3.7344

Max Act: 3.4368. Min Act: -0.1700

Data Index: 1173657 (C4 (Web Text))

Max Activating Token Index: 98