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

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

Neuron 450 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: 4.7852. Min Range: -4.7852

Max Act: 4.7852. Min Act: -0.1699

Data Index: 1279825 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.7683. Min Act: -0.1700

Data Index: 760757 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.7518. Min Act: -0.1697

Data Index: 1025371 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.7460. Min Act: -0.1700

Data Index: 765599 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.7147. Min Act: -0.1700

Data Index: 1139549 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.7110. Min Act: -0.1700

Data Index: 679419 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.7314. Min Act: -0.1700

Data Index: 445944 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6580. Min Act: -0.1678

Data Index: 284835 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6493. Min Act: -0.1700

Data Index: 237610 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6696. Min Act: -0.1700

Data Index: 717032 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6435. Min Act: -0.1687

Data Index: 692518 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6411. Min Act: -0.1700

Data Index: 1226479 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6117. Min Act: -0.1679

Data Index: 176555 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5848. Min Act: -0.1683

Data Index: 154321 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6044. Min Act: -0.1699

Data Index: 214177 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6059. Min Act: -0.1700

Data Index: 1002093 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5948. Min Act: -0.1698

Data Index: 765722 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5920. Min Act: -0.1700

Data Index: 221960 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6025. Min Act: -0.1700

Data Index: 736234 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5925. Min Act: -0.1699

Data Index: 774743 (C4 (Web Text))

Max Activating Token Index: 412