Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2107 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9885. Min Act: -0.1700

Data Index: 7218814 (Open Web Text)

Max Activating Token Index: 875

Text #1

Max Range: 3.0022. Min Range: -3.0022

Max Act: 3.0022. Min Act: -0.1700

Data Index: 6393179 (Open Web Text)

Max Activating Token Index: 876

Text #2

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9857. Min Act: -0.1700

Data Index: 1900918 (Open Web Text)

Max Activating Token Index: 984

Text #3

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9706. Min Act: -0.1700

Data Index: 5062338 (Open Web Text)

Max Activating Token Index: 846

Text #4

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9375. Min Act: -0.1700

Data Index: 119535 (Open Web Text)

Max Activating Token Index: 830

Text #5

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9375. Min Act: -0.1700

Data Index: 6184604 (Open Web Text)

Max Activating Token Index: 729

Text #6

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9020. Min Act: -0.1700

Data Index: 827639 (Open Web Text)

Max Activating Token Index: 649

Text #7

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.9165. Min Act: -0.1700

Data Index: 7462436 (Open Web Text)

Max Activating Token Index: 971

Text #8

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8697. Min Act: -0.1700

Data Index: 1770737 (Open Web Text)

Max Activating Token Index: 652

Text #9

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8776. Min Act: -0.1700

Data Index: 5966663 (Open Web Text)

Max Activating Token Index: 553

Text #10

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8692. Min Act: -0.1700

Data Index: 681567 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8656. Min Act: -0.1700

Data Index: 7462432 (Open Web Text)

Max Activating Token Index: 732

Text #12

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8715. Min Act: -0.1700

Data Index: 2188134 (Open Web Text)

Max Activating Token Index: 665

Text #13

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8332. Min Act: -0.1700

Data Index: 7462429 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8520. Min Act: -0.1700

Data Index: 4915794 (Open Web Text)

Max Activating Token Index: 513

Text #15

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8206. Min Act: -0.1700

Data Index: 5673285 (Open Web Text)

Max Activating Token Index: 464

Text #16

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8387. Min Act: -0.1700

Data Index: 3700842 (Open Web Text)

Max Activating Token Index: 917

Text #17

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8125. Min Act: -0.1700

Data Index: 7504024 (Open Web Text)

Max Activating Token Index: 540

Text #18

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8049. Min Act: -0.1700

Data Index: 1389179 (Open Web Text)

Max Activating Token Index: 858

Text #19

Max Range: 3.0022. Min Range: -3.0022

Max Act: 2.8111. Min Act: -0.1700

Data Index: 5930726 (Open Web Text)

Max Activating Token Index: 781