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

Dataset: Open Web Text

Neuron 1561 in Layer 4

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: 3.0519. Min Range: -3.0519

Max Act: 3.0363. Min Act: -0.1700

Data Index: 165815 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 3.0519. Min Range: -3.0519

Max Act: 3.0519. Min Act: -0.1700

Data Index: 1195543 (Open Web Text)

Max Activating Token Index: 587

Text #2

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9980. Min Act: -0.1700

Data Index: 7908028 (Open Web Text)

Max Activating Token Index: 224

Text #3

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9892. Min Act: -0.1700

Data Index: 4934584 (Open Web Text)

Max Activating Token Index: 692

Text #4

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1296178 (Open Web Text)

Max Activating Token Index: 287

Text #5

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9767. Min Act: -0.1700

Data Index: 1816352 (Open Web Text)

Max Activating Token Index: 229

Text #6

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9796. Min Act: -0.1700

Data Index: 5818733 (Open Web Text)

Max Activating Token Index: 652

Text #7

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9832. Min Act: -0.1700

Data Index: 7401929 (Open Web Text)

Max Activating Token Index: 990

Text #8

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9524. Min Act: -0.1700

Data Index: 8585384 (Open Web Text)

Max Activating Token Index: 775

Text #9

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9446. Min Act: -0.1700

Data Index: 4924761 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9183. Min Act: -0.1700

Data Index: 2909907 (Open Web Text)

Max Activating Token Index: 576

Text #11

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9303. Min Act: -0.1700

Data Index: 2561724 (Open Web Text)

Max Activating Token Index: 707

Text #12

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9332. Min Act: -0.1700

Data Index: 3499950 (Open Web Text)

Max Activating Token Index: 539

Text #13

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9106. Min Act: -0.1700

Data Index: 6139673 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9117. Min Act: -0.1700

Data Index: 4335194 (Open Web Text)

Max Activating Token Index: 982

Text #15

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.8955. Min Act: -0.1700

Data Index: 5998863 (Open Web Text)

Max Activating Token Index: 374

Text #16

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9037. Min Act: -0.1700

Data Index: 3611553 (Open Web Text)

Max Activating Token Index: 703

Text #17

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.8922. Min Act: -0.1700

Data Index: 300243 (Open Web Text)

Max Activating Token Index: 83

Text #18

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9065. Min Act: -0.1700

Data Index: 6036586 (Open Web Text)

Max Activating Token Index: 854

Text #19

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.9265. Min Act: -0.1700

Data Index: 4299561 (Open Web Text)

Max Activating Token Index: 368