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

Dataset: Open Web Text

Neuron 1999 in Layer 0

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: 1.9082. Min Range: -1.9082

Max Act: 1.9082. Min Act: -0.1699

Data Index: 3071950 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.8783. Min Act: -0.1697

Data Index: 6117995 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.8473. Min Act: -0.1511

Data Index: 4924721 (Open Web Text)

Max Activating Token Index: 274

Text #3

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.8413. Min Act: -0.1700

Data Index: 3550679 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.8449. Min Act: -0.1671

Data Index: 1286183 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.8213. Min Act: -0.1599

Data Index: 3260116 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.8122. Min Act: -0.1698

Data Index: 3337072 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.8122. Min Act: -0.1675

Data Index: 8679638 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.8104. Min Act: -0.1689

Data Index: 82264 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7997. Min Act: -0.1612

Data Index: 6332526 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7922. Min Act: -0.1695

Data Index: 7452726 (Open Web Text)

Max Activating Token Index: 490

Text #11

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7958. Min Act: -0.1428

Data Index: 6945428 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7988. Min Act: -0.1700

Data Index: 700650 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7839. Min Act: -0.1695

Data Index: 6121457 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7855. Min Act: -0.1698

Data Index: 625033 (Open Web Text)

Max Activating Token Index: 513

Text #15

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7862. Min Act: -0.1700

Data Index: 6675151 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7833. Min Act: -0.1700

Data Index: 2608684 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7824. Min Act: -0.1647

Data Index: 1275428 (Open Web Text)

Max Activating Token Index: 827

Text #18

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7813. Min Act: -0.1690

Data Index: 1193355 (Open Web Text)

Max Activating Token Index: 169

Text #19

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.7804. Min Act: -0.1631

Data Index: 1826855 (Open Web Text)

Max Activating Token Index: 75