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

Dataset: Open Web Text

Neuron 2192 in Layer 2

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: 1.8719. Min Range: -1.8719

Max Act: 1.8719. Min Act: -0.1700

Data Index: 8344749 (Open Web Text)

Max Activating Token Index: 286

Text #1

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7955. Min Act: -0.1700

Data Index: 949140 (Open Web Text)

Max Activating Token Index: 607

Text #2

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7767. Min Act: -0.1700

Data Index: 4441688 (Open Web Text)

Max Activating Token Index: 219

Text #3

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7624. Min Act: -0.1700

Data Index: 1352326 (Open Web Text)

Max Activating Token Index: 363

Text #4

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7370. Min Act: -0.1700

Data Index: 2387832 (Open Web Text)

Max Activating Token Index: 572

Text #5

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7528. Min Act: -0.1700

Data Index: 3609555 (Open Web Text)

Max Activating Token Index: 106

Text #6

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7360. Min Act: -0.1700

Data Index: 5338456 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.6956. Min Act: -0.1700

Data Index: 5553350 (Open Web Text)

Max Activating Token Index: 413

Text #8

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7051. Min Act: -0.1700

Data Index: 8075446 (Open Web Text)

Max Activating Token Index: 280

Text #9

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7037. Min Act: -0.1700

Data Index: 6421880 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7209. Min Act: -0.1700

Data Index: 964969 (Open Web Text)

Max Activating Token Index: 310

Text #11

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7016. Min Act: -0.1700

Data Index: 6761513 (Open Web Text)

Max Activating Token Index: 691

Text #12

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.6911. Min Act: -0.1700

Data Index: 1273806 (Open Web Text)

Max Activating Token Index: 310

Text #13

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7048. Min Act: -0.1700

Data Index: 288606 (Open Web Text)

Max Activating Token Index: 103

Text #14

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.6983. Min Act: -0.1700

Data Index: 2158224 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7136. Min Act: -0.1700

Data Index: 4854979 (Open Web Text)

Max Activating Token Index: 614

Text #16

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7033. Min Act: -0.1700

Data Index: 1340917 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7065. Min Act: -0.1700

Data Index: 1611888 (Open Web Text)

Max Activating Token Index: 895

Text #18

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.6951. Min Act: -0.1700

Data Index: 4014815 (Open Web Text)

Max Activating Token Index: 722

Text #19

Max Range: 1.8719. Min Range: -1.8719

Max Act: 1.7023. Min Act: -0.1700

Data Index: 3499119 (Open Web Text)

Max Activating Token Index: 167