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

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

Neuron 812 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: 2.9633. Min Range: -2.9633

Max Act: 2.9633. Min Act: -0.1700

Data Index: 891075 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.9369. Min Act: -0.1700

Data Index: 1121683 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.9219. Min Act: -0.1700

Data Index: 1389417 (Python Code)

Max Activating Token Index: 582

Text #3

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.8154. Min Act: -0.1700

Data Index: 1655477 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.7991. Min Act: -0.1700

Data Index: 1381371 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.7949. Min Act: -0.1700

Data Index: 1245483 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.7610. Min Act: -0.1700

Data Index: 892216 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.7068. Min Act: -0.1700

Data Index: 862732 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.7057. Min Act: -0.1700

Data Index: 1517640 (Python Code)

Max Activating Token Index: 128

Text #9

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.7096. Min Act: -0.1700

Data Index: 1410869 (Python Code)

Max Activating Token Index: 919

Text #10

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.6873. Min Act: -0.1700

Data Index: 1575783 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.6907. Min Act: -0.1700

Data Index: 1564675 (Python Code)

Max Activating Token Index: 527

Text #12

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.6812. Min Act: -0.1700

Data Index: 1486759 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.6704. Min Act: -0.1700

Data Index: 1618506 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.6709. Min Act: -0.1700

Data Index: 450596 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.6795. Min Act: -0.1700

Data Index: 1181607 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.6817. Min Act: -0.1700

Data Index: 1624080 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.6695. Min Act: -0.1700

Data Index: 1587791 (Python Code)

Max Activating Token Index: 512

Text #18

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.6544. Min Act: -0.1700

Data Index: 1508685 (Python Code)

Max Activating Token Index: 94

Text #19

Max Range: 2.9633. Min Range: -2.9633

Max Act: 2.6767. Min Act: -0.1700

Data Index: 497230 (C4 (Web Text))

Max Activating Token Index: 1020