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

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

Neuron 1450 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.8706. Min Act: -0.1700

Data Index: 375909 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.5268. Min Act: -0.1700

Data Index: 433170 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.3393. Min Act: -0.1700

Data Index: 1176038 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.3081. Min Act: -0.1700

Data Index: 785129 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.3393. Min Act: -0.1700

Data Index: 670513 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.2456. Min Act: -0.1700

Data Index: 1162844 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.2143. Min Act: -0.1700

Data Index: 283216 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.2143. Min Act: -0.1700

Data Index: 819258 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.1831. Min Act: -0.1700

Data Index: 1283340 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.1518. Min Act: -0.1700

Data Index: 350595 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.0893. Min Act: -0.1700

Data Index: 217711 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.1518. Min Act: -0.1700

Data Index: 283585 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.0893. Min Act: -0.1700

Data Index: 289074 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.0893. Min Act: -0.1700

Data Index: 1140455 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.0268. Min Act: -0.1700

Data Index: 563454 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.0581. Min Act: -0.1700

Data Index: 19037 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.0893. Min Act: -0.1700

Data Index: 199009 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.0893. Min Act: -0.1700

Data Index: 130345 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.0893. Min Act: -0.1700

Data Index: 852137 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 5.8706. Min Range: -5.8706

Max Act: 5.1206. Min Act: -0.1700

Data Index: 357778 (C4 (Web Text))

Max Activating Token Index: 598