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

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

Neuron 1945 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: 3.4670. Min Range: -3.4670

Max Act: 3.4513. Min Act: -0.1700

Data Index: 976187 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.4670. Min Act: -0.1700

Data Index: 1383767 (Python Code)

Max Activating Token Index: 510

Text #2

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3886. Min Act: -0.1700

Data Index: 793778 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3572. Min Act: -0.1700

Data Index: 504476 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3415. Min Act: -0.1700

Data Index: 498996 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3729. Min Act: -0.1700

Data Index: 123356 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3729. Min Act: -0.1700

Data Index: 1341270 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3572. Min Act: -0.1700

Data Index: 402376 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3101. Min Act: -0.1700

Data Index: 1244088 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2787. Min Act: -0.1700

Data Index: 1063354 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3572. Min Act: -0.1700

Data Index: 861845 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3101. Min Act: -0.1700

Data Index: 475571 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2944. Min Act: -0.1700

Data Index: 962160 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3258. Min Act: -0.1700

Data Index: 1058747 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2787. Min Act: -0.1700

Data Index: 228711 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3101. Min Act: -0.1700

Data Index: 424991 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2473. Min Act: -0.1700

Data Index: 1402179 (Python Code)

Max Activating Token Index: 552

Text #17

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2787. Min Act: -0.1700

Data Index: 1601864 (Python Code)

Max Activating Token Index: 646

Text #18

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2316. Min Act: -0.1700

Data Index: 173454 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2944. Min Act: -0.1700

Data Index: 1120478 (C4 (Web Text))

Max Activating Token Index: 660