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

Dataset: Open Web Text

Neuron 2973 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: 4.4755. Min Range: -4.4755

Max Act: 4.4755. Min Act: -0.1700

Data Index: 402062 (Open Web Text)

Max Activating Token Index: 912

Text #1

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.4028. Min Act: -0.1700

Data Index: 8802312 (Open Web Text)

Max Activating Token Index: 576

Text #2

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.2478. Min Act: -0.1700

Data Index: 2122040 (Open Web Text)

Max Activating Token Index: 808

Text #3

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.2707. Min Act: -0.1700

Data Index: 7606300 (Open Web Text)

Max Activating Token Index: 551

Text #4

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.2167. Min Act: -0.1700

Data Index: 1114832 (Open Web Text)

Max Activating Token Index: 159

Text #5

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1644. Min Act: -0.1700

Data Index: 7705329 (Open Web Text)

Max Activating Token Index: 720

Text #6

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1454. Min Act: -0.1700

Data Index: 8733314 (Open Web Text)

Max Activating Token Index: 375

Text #7

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1815. Min Act: -0.1700

Data Index: 8063335 (Open Web Text)

Max Activating Token Index: 327

Text #8

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1920. Min Act: -0.1700

Data Index: 63785 (Open Web Text)

Max Activating Token Index: 694

Text #9

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1668. Min Act: -0.1700

Data Index: 6894692 (Open Web Text)

Max Activating Token Index: 942

Text #10

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1706. Min Act: -0.1700

Data Index: 4540183 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1954. Min Act: -0.1700

Data Index: 6608424 (Open Web Text)

Max Activating Token Index: 56

Text #12

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1374. Min Act: -0.1700

Data Index: 6466488 (Open Web Text)

Max Activating Token Index: 816

Text #13

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1571. Min Act: -0.1700

Data Index: 2861966 (Open Web Text)

Max Activating Token Index: 1011

Text #14

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1578. Min Act: -0.1700

Data Index: 2936152 (Open Web Text)

Max Activating Token Index: 803

Text #15

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1681. Min Act: -0.1700

Data Index: 4691919 (Open Web Text)

Max Activating Token Index: 876

Text #16

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1320. Min Act: -0.1700

Data Index: 6688673 (Open Web Text)

Max Activating Token Index: 309

Text #17

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1674. Min Act: -0.1700

Data Index: 4026113 (Open Web Text)

Max Activating Token Index: 241

Text #18

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1720. Min Act: -0.1700

Data Index: 1251872 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 4.4755. Min Range: -4.4755

Max Act: 4.1180. Min Act: -0.1700

Data Index: 1189133 (Open Web Text)

Max Activating Token Index: 250