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

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

Neuron 789 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: 3.3867. Min Range: -3.3867

Max Act: 3.3867. Min Act: -0.1700

Data Index: 636342 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.3397. Min Act: -0.1700

Data Index: 1317425 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.3240. Min Act: -0.1700

Data Index: 300177 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2768. Min Act: -0.1700

Data Index: 212903 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2925. Min Act: -0.1700

Data Index: 353511 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2454. Min Act: -0.1700

Data Index: 573150 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2925. Min Act: -0.1700

Data Index: 436201 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2768. Min Act: -0.1700

Data Index: 148703 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2297. Min Act: -0.1700

Data Index: 445041 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2297. Min Act: -0.1700

Data Index: 917837 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2297. Min Act: -0.1700

Data Index: 311321 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2454. Min Act: -0.1700

Data Index: 845710 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2454. Min Act: -0.1700

Data Index: 109005 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2454. Min Act: -0.1700

Data Index: 311477 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.1982. Min Act: -0.1700

Data Index: 1080687 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2454. Min Act: -0.1700

Data Index: 492004 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2140. Min Act: -0.1700

Data Index: 1203463 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.2297. Min Act: -0.1700

Data Index: 842473 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.1825. Min Act: -0.1700

Data Index: 576625 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 3.3867. Min Range: -3.3867

Max Act: 3.1982. Min Act: -0.1700

Data Index: 1203172 (C4 (Web Text))

Max Activating Token Index: 637