Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 503 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.5600. Min Act: -0.1700

Data Index: 120460 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.5393. Min Act: -0.1700

Data Index: 516476 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.4167. Min Act: -0.1700

Data Index: 298583 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.4131. Min Act: -0.1700

Data Index: 938063 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.4126. Min Act: -0.1700

Data Index: 1270354 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.4046. Min Act: -0.1700

Data Index: 1334115 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.4007. Min Act: -0.1700

Data Index: 1140327 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3951. Min Act: -0.1700

Data Index: 757350 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.4099. Min Act: -0.1700

Data Index: 1334702 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3698. Min Act: -0.1700

Data Index: 145878 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3996. Min Act: -0.1700

Data Index: 921210 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3723. Min Act: -0.1700

Data Index: 773569 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3770. Min Act: -0.1700

Data Index: 180563 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3604. Min Act: -0.1700

Data Index: 555983 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3753. Min Act: -0.1700

Data Index: 842371 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3824. Min Act: -0.1700

Data Index: 963288 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3541. Min Act: -0.1700

Data Index: 105545 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3473. Min Act: -0.1700

Data Index: 1204633 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3442. Min Act: -0.1700

Data Index: 738021 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 3.5600. Min Range: -3.5600

Max Act: 3.3620. Min Act: -0.1700

Data Index: 138142 (C4 (Web Text))

Max Activating Token Index: 923