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

Dataset: Open Web Text

Neuron 1971 in Layer 1

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: 1.9530. Min Range: -1.9530

Max Act: 1.9530. Min Act: -0.1700

Data Index: 5613823 (Open Web Text)

Max Activating Token Index: 77

Text #1

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.9264. Min Act: -0.1700

Data Index: 4519356 (Open Web Text)

Max Activating Token Index: 825

Text #2

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.9311. Min Act: -0.1700

Data Index: 3404146 (Open Web Text)

Max Activating Token Index: 925

Text #3

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.9375. Min Act: -0.1699

Data Index: 3541272 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.9079. Min Act: -0.1689

Data Index: 3956878 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.9104. Min Act: -0.1692

Data Index: 1337671 (Open Web Text)

Max Activating Token Index: 971

Text #6

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8968. Min Act: -0.1699

Data Index: 1658841 (Open Web Text)

Max Activating Token Index: 86

Text #7

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8960. Min Act: -0.1700

Data Index: 6499951 (Open Web Text)

Max Activating Token Index: 181

Text #8

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8925. Min Act: -0.1700

Data Index: 7428990 (Open Web Text)

Max Activating Token Index: 819

Text #9

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8824. Min Act: -0.1700

Data Index: 6341532 (Open Web Text)

Max Activating Token Index: 80

Text #10

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8885. Min Act: -0.1697

Data Index: 3841868 (Open Web Text)

Max Activating Token Index: 696

Text #11

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.9043. Min Act: -0.1700

Data Index: 973533 (Open Web Text)

Max Activating Token Index: 897

Text #12

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8805. Min Act: -0.1700

Data Index: 657897 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8697. Min Act: -0.1700

Data Index: 6295557 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8839. Min Act: -0.1681

Data Index: 6191992 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8770. Min Act: -0.1700

Data Index: 1502770 (Open Web Text)

Max Activating Token Index: 502

Text #16

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8768. Min Act: -0.1700

Data Index: 3524945 (Open Web Text)

Max Activating Token Index: 206

Text #17

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8837. Min Act: -0.1700

Data Index: 26693 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8896. Min Act: -0.1700

Data Index: 3430831 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8806. Min Act: -0.1698

Data Index: 3066694 (Open Web Text)

Max Activating Token Index: 553