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

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

Neuron 1024 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: 4.1907. Min Range: -4.1907

Max Act: 4.1907. Min Act: -0.1700

Data Index: 815568 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 4.1907. Min Range: -4.1907

Max Act: 4.1594. Min Act: -0.1700

Data Index: 556745 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 4.1907. Min Range: -4.1907

Max Act: 4.1594. Min Act: -0.1700

Data Index: 762946 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 4.1907. Min Range: -4.1907

Max Act: 4.0344. Min Act: -0.1700

Data Index: 1297309 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 4.1907. Min Range: -4.1907

Max Act: 4.0657. Min Act: -0.1700

Data Index: 505634 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9719. Min Act: -0.1700

Data Index: 902805 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9719. Min Act: -0.1700

Data Index: 1209768 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9719. Min Act: -0.1700

Data Index: 39362 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9719. Min Act: -0.1700

Data Index: 168589 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9093. Min Act: -0.1700

Data Index: 1050145 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9093. Min Act: -0.1700

Data Index: 979425 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9093. Min Act: -0.1700

Data Index: 536488 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9719. Min Act: -0.1700

Data Index: 1081148 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.8780. Min Act: -0.1700

Data Index: 14375 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9406. Min Act: -0.1700

Data Index: 1088429 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9093. Min Act: -0.1700

Data Index: 1141342 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.8780. Min Act: -0.1700

Data Index: 819937 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.9093. Min Act: -0.1700

Data Index: 508467 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.8780. Min Act: -0.1700

Data Index: 692910 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.8468. Min Act: -0.1700

Data Index: 590676 (C4 (Web Text))

Max Activating Token Index: 636