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

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

Neuron 890 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: 2.9587. Min Range: -2.9587

Max Act: 2.9587. Min Act: -0.1700

Data Index: 1028774 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.9474. Min Act: -0.1700

Data Index: 588146 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.8697. Min Act: -0.1700

Data Index: 779358 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.8275. Min Act: -0.1700

Data Index: 144412 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.8339. Min Act: -0.1700

Data Index: 67207 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.8344. Min Act: -0.1700

Data Index: 692964 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.8082. Min Act: -0.1700

Data Index: 1269946 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.8028. Min Act: -0.1700

Data Index: 887419 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7894. Min Act: -0.1700

Data Index: 1287046 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7983. Min Act: -0.1700

Data Index: 655730 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7941. Min Act: -0.1700

Data Index: 814374 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7572. Min Act: -0.1700

Data Index: 645738 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7863. Min Act: -0.1700

Data Index: 866428 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7655. Min Act: -0.1700

Data Index: 1045621 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7524. Min Act: -0.1700

Data Index: 483459 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7519. Min Act: -0.1700

Data Index: 168196 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7714. Min Act: -0.1700

Data Index: 1039329 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7451. Min Act: -0.1700

Data Index: 497686 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7314. Min Act: -0.1700

Data Index: 500762 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 2.9587. Min Range: -2.9587

Max Act: 2.7466. Min Act: -0.1700

Data Index: 1094895 (C4 (Web Text))

Max Activating Token Index: 720