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

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

Neuron 1346 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: 3.9882. Min Range: -3.9882

Max Act: 3.9882. Min Act: -0.1700

Data Index: 130676 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.9570. Min Act: -0.1700

Data Index: 148482 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.8944. Min Act: -0.1700

Data Index: 984448 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.9570. Min Act: -0.1700

Data Index: 703095 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.9257. Min Act: -0.1700

Data Index: 37719 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.8319. Min Act: -0.1700

Data Index: 1105680 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.8319. Min Act: -0.1700

Data Index: 585063 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.8006. Min Act: -0.1700

Data Index: 516369 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7693. Min Act: -0.1700

Data Index: 1147146 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7693. Min Act: -0.1700

Data Index: 242932 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7693. Min Act: -0.1700

Data Index: 1151830 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7380. Min Act: -0.1700

Data Index: 102408 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7380. Min Act: -0.1700

Data Index: 449610 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7067. Min Act: -0.1700

Data Index: 1149925 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7067. Min Act: -0.1700

Data Index: 452318 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7380. Min Act: -0.1700

Data Index: 741077 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7693. Min Act: -0.1700

Data Index: 1229690 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7380. Min Act: -0.1700

Data Index: 358020 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.6441. Min Act: -0.1700

Data Index: 25960 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 3.9882. Min Range: -3.9882

Max Act: 3.7067. Min Act: -0.1700

Data Index: 612203 (C4 (Web Text))

Max Activating Token Index: 853