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

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

Neuron 1103 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: 3.9760. Min Range: -3.9760

Max Act: 3.9760. Min Act: -0.1700

Data Index: 17662 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.9135. Min Act: -0.1700

Data Index: 882997 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.8509. Min Act: -0.1700

Data Index: 495341 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7884. Min Act: -0.1700

Data Index: 335154 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.8509. Min Act: -0.1700

Data Index: 325951 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.8509. Min Act: -0.1700

Data Index: 13174 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7571. Min Act: -0.1700

Data Index: 568793 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7258. Min Act: -0.1700

Data Index: 791227 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.8196. Min Act: -0.1700

Data Index: 673934 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.8196. Min Act: -0.1700

Data Index: 105945 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7571. Min Act: -0.1700

Data Index: 1061640 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7571. Min Act: -0.1700

Data Index: 756137 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.8196. Min Act: -0.1700

Data Index: 923363 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7884. Min Act: -0.1700

Data Index: 1235256 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7884. Min Act: -0.1700

Data Index: 1322681 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7571. Min Act: -0.1700

Data Index: 566947 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7258. Min Act: -0.1700

Data Index: 827814 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7571. Min Act: -0.1700

Data Index: 81122 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7258. Min Act: -0.1700

Data Index: 924581 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 3.9760. Min Range: -3.9760

Max Act: 3.7884. Min Act: -0.1700

Data Index: 954756 (C4 (Web Text))

Max Activating Token Index: 75