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

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

Neuron 1082 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: 3.1487. Min Range: -3.1487

Max Act: 3.1487. Min Act: -0.1700

Data Index: 1341851 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 3.1487. Min Range: -3.1487

Max Act: 3.1014. Min Act: -0.1700

Data Index: 635994 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 3.1487. Min Range: -3.1487

Max Act: 3.1014. Min Act: -0.1700

Data Index: 693605 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 3.1487. Min Range: -3.1487

Max Act: 3.0383. Min Act: -0.1700

Data Index: 1028259 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 3.1487. Min Range: -3.1487

Max Act: 3.0699. Min Act: -0.1700

Data Index: 529987 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 3.1487. Min Range: -3.1487

Max Act: 3.0541. Min Act: -0.1700

Data Index: 841829 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.1487. Min Range: -3.1487

Max Act: 3.0225. Min Act: -0.1700

Data Index: 525499 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 3.1487. Min Range: -3.1487

Max Act: 3.0067. Min Act: -0.1700

Data Index: 486360 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.9909. Min Act: -0.1700

Data Index: 1052777 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.9434. Min Act: -0.1700

Data Index: 21066 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.9909. Min Act: -0.1700

Data Index: 1109828 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 3.1487. Min Range: -3.1487

Max Act: 3.1014. Min Act: -0.1700

Data Index: 945755 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.9909. Min Act: -0.1700

Data Index: 266452 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.9751. Min Act: -0.1700

Data Index: 960360 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.9434. Min Act: -0.1700

Data Index: 482066 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.9593. Min Act: -0.1700

Data Index: 745347 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.9276. Min Act: -0.1700

Data Index: 1356299 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.9434. Min Act: -0.1700

Data Index: 1205171 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.9117. Min Act: -0.1700

Data Index: 977249 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 3.1487. Min Range: -3.1487

Max Act: 2.8959. Min Act: -0.1700

Data Index: 183529 (C4 (Web Text))

Max Activating Token Index: 794