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

Dataset: Open Web Text

Neuron 1727 in Layer 5

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: 3.4923. Min Range: -3.4923

Max Act: 3.4923. Min Act: -0.1700

Data Index: 6121944 (Open Web Text)

Max Activating Token Index: 913

Text #1

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.4453. Min Act: -0.1700

Data Index: 3283681 (Open Web Text)

Max Activating Token Index: 798

Text #2

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3793. Min Act: -0.1700

Data Index: 5677816 (Open Web Text)

Max Activating Token Index: 101

Text #3

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3968. Min Act: -0.1700

Data Index: 6635463 (Open Web Text)

Max Activating Token Index: 453

Text #4

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3872. Min Act: -0.1700

Data Index: 5501227 (Open Web Text)

Max Activating Token Index: 949

Text #5

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3692. Min Act: -0.1700

Data Index: 1346601 (Open Web Text)

Max Activating Token Index: 858

Text #6

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3268. Min Act: -0.1700

Data Index: 35290 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3210. Min Act: -0.1700

Data Index: 2481411 (Open Web Text)

Max Activating Token Index: 559

Text #8

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3505. Min Act: -0.1700

Data Index: 7937693 (Open Web Text)

Max Activating Token Index: 723

Text #9

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3327. Min Act: -0.1700

Data Index: 3821619 (Open Web Text)

Max Activating Token Index: 674

Text #10

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3148. Min Act: -0.1700

Data Index: 6196728 (Open Web Text)

Max Activating Token Index: 335

Text #11

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3164. Min Act: -0.1700

Data Index: 8054080 (Open Web Text)

Max Activating Token Index: 96

Text #12

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2805. Min Act: -0.1700

Data Index: 5146305 (Open Web Text)

Max Activating Token Index: 660

Text #13

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3047. Min Act: -0.1700

Data Index: 1619411 (Open Web Text)

Max Activating Token Index: 189

Text #14

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3244. Min Act: -0.1700

Data Index: 4390162 (Open Web Text)

Max Activating Token Index: 580

Text #15

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2411. Min Act: -0.1700

Data Index: 3339395 (Open Web Text)

Max Activating Token Index: 764

Text #16

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2794. Min Act: -0.1700

Data Index: 3602979 (Open Web Text)

Max Activating Token Index: 160

Text #17

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2985. Min Act: -0.1700

Data Index: 4788934 (Open Web Text)

Max Activating Token Index: 676

Text #18

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2719. Min Act: -0.1700

Data Index: 238769 (Open Web Text)

Max Activating Token Index: 954

Text #19

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2387. Min Act: -0.1700

Data Index: 1227081 (Open Web Text)

Max Activating Token Index: 772