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

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

Neuron 1572 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2530. Min Range: -5.2530

Max Act: 5.2530. Min Act: -0.1700

Data Index: 304341 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 5.2530. Min Range: -5.2530

Max Act: 5.0655. Min Act: -0.1700

Data Index: 613938 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9405. Min Act: -0.1700

Data Index: 473736 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9405. Min Act: -0.1700

Data Index: 457328 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9405. Min Act: -0.1700

Data Index: 1275945 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9717. Min Act: -0.1700

Data Index: 245322 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9405. Min Act: -0.1700

Data Index: 632780 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9092. Min Act: -0.1700

Data Index: 626848 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9405. Min Act: -0.1700

Data Index: 545199 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9405. Min Act: -0.1700

Data Index: 32132 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9717. Min Act: -0.1700

Data Index: 744112 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9092. Min Act: -0.1700

Data Index: 927954 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.8780. Min Act: -0.1700

Data Index: 1067314 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.9405. Min Act: -0.1700

Data Index: 606091 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.8467. Min Act: -0.1700

Data Index: 1196945 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.8780. Min Act: -0.1700

Data Index: 873895 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.8467. Min Act: -0.1700

Data Index: 1071378 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.8780. Min Act: -0.1700

Data Index: 815990 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.8467. Min Act: -0.1700

Data Index: 239458 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 5.2530. Min Range: -5.2530

Max Act: 4.8155. Min Act: -0.1700

Data Index: 352799 (C4 (Web Text))

Max Activating Token Index: 537