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

Dataset: Open Web Text

Neuron 1547 in Layer 4

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: 5.6833. Min Range: -5.6833

Max Act: 5.6833. Min Act: -0.1700

Data Index: 1552238 (Open Web Text)

Max Activating Token Index: 328

Text #1

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.6643. Min Act: -0.1700

Data Index: 5468777 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.6439. Min Act: -0.1700

Data Index: 8608723 (Open Web Text)

Max Activating Token Index: 245

Text #3

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5844. Min Act: -0.1700

Data Index: 8334875 (Open Web Text)

Max Activating Token Index: 440

Text #4

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5529. Min Act: -0.1700

Data Index: 452735 (Open Web Text)

Max Activating Token Index: 995

Text #5

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.6443. Min Act: -0.1700

Data Index: 7177638 (Open Web Text)

Max Activating Token Index: 294

Text #6

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5833. Min Act: -0.1700

Data Index: 5189907 (Open Web Text)

Max Activating Token Index: 971

Text #7

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5181. Min Act: -0.1700

Data Index: 1911648 (Open Web Text)

Max Activating Token Index: 411

Text #8

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.5064. Min Act: -0.1700

Data Index: 4550450 (Open Web Text)

Max Activating Token Index: 270

Text #9

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4706. Min Act: -0.1700

Data Index: 82982 (Open Web Text)

Max Activating Token Index: 768

Text #10

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4494. Min Act: -0.1700

Data Index: 5368415 (Open Web Text)

Max Activating Token Index: 316

Text #11

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4229. Min Act: -0.1700

Data Index: 653079 (Open Web Text)

Max Activating Token Index: 388

Text #12

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4470. Min Act: -0.1700

Data Index: 6168529 (Open Web Text)

Max Activating Token Index: 67

Text #13

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4506. Min Act: -0.1700

Data Index: 1260916 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4413. Min Act: -0.1700

Data Index: 4021057 (Open Web Text)

Max Activating Token Index: 816

Text #15

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.4059. Min Act: -0.1700

Data Index: 5677156 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.3873. Min Act: -0.1700

Data Index: 8094949 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.3758. Min Act: -0.1700

Data Index: 743672 (Open Web Text)

Max Activating Token Index: 718

Text #18

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.3670. Min Act: -0.1700

Data Index: 2148149 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 5.6833. Min Range: -5.6833

Max Act: 5.3645. Min Act: -0.1700

Data Index: 4300141 (Open Web Text)

Max Activating Token Index: 12