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

Dataset: Open Web Text

Neuron 1847 in Layer 6

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: 5.0049. Min Range: -5.0049

Max Act: 4.9699. Min Act: -0.1700

Data Index: 87889 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 5.0049. Min Range: -5.0049

Max Act: 5.0049. Min Act: -0.1700

Data Index: 3977887 (Open Web Text)

Max Activating Token Index: 664

Text #2

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.9492. Min Act: -0.1700

Data Index: 7634463 (Open Web Text)

Max Activating Token Index: 670

Text #3

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.9129. Min Act: -0.1700

Data Index: 1291405 (Open Web Text)

Max Activating Token Index: 572

Text #4

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.8594. Min Act: -0.1700

Data Index: 3014373 (Open Web Text)

Max Activating Token Index: 113

Text #5

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.8317. Min Act: -0.1700

Data Index: 8423490 (Open Web Text)

Max Activating Token Index: 276

Text #6

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.8228. Min Act: -0.1700

Data Index: 6348867 (Open Web Text)

Max Activating Token Index: 170

Text #7

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.8352. Min Act: -0.1700

Data Index: 4979081 (Open Web Text)

Max Activating Token Index: 235

Text #8

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.8179. Min Act: -0.1700

Data Index: 7488437 (Open Web Text)

Max Activating Token Index: 937

Text #9

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.8068. Min Act: -0.1700

Data Index: 3786291 (Open Web Text)

Max Activating Token Index: 30

Text #10

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.8197. Min Act: -0.1700

Data Index: 614702 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.7921. Min Act: -0.1700

Data Index: 8239827 (Open Web Text)

Max Activating Token Index: 227

Text #12

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.7878. Min Act: -0.1700

Data Index: 4551829 (Open Web Text)

Max Activating Token Index: 106

Text #13

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.8067. Min Act: -0.1700

Data Index: 8511128 (Open Web Text)

Max Activating Token Index: 240

Text #14

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.7890. Min Act: -0.1700

Data Index: 2390624 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.7614. Min Act: -0.1700

Data Index: 4167825 (Open Web Text)

Max Activating Token Index: 421

Text #16

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.7594. Min Act: -0.1700

Data Index: 7439038 (Open Web Text)

Max Activating Token Index: 815

Text #17

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.7727. Min Act: -0.1700

Data Index: 5908406 (Open Web Text)

Max Activating Token Index: 906

Text #18

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.7591. Min Act: -0.1700

Data Index: 2737802 (Open Web Text)

Max Activating Token Index: 719

Text #19

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.7102. Min Act: -0.1700

Data Index: 4671336 (Open Web Text)

Max Activating Token Index: 706