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

Dataset: Open Web Text

Neuron 1645 in Layer 3

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: 5.1463. Min Range: -5.1463

Max Act: 5.1463. Min Act: -0.1700

Data Index: 549673 (Open Web Text)

Max Activating Token Index: 622

Text #1

Max Range: 5.1463. Min Range: -5.1463

Max Act: 5.1112. Min Act: -0.1700

Data Index: 8649890 (Open Web Text)

Max Activating Token Index: 343

Text #2

Max Range: 5.1463. Min Range: -5.1463

Max Act: 5.1297. Min Act: -0.1700

Data Index: 2937097 (Open Web Text)

Max Activating Token Index: 152

Text #3

Max Range: 5.1463. Min Range: -5.1463

Max Act: 5.0835. Min Act: -0.1700

Data Index: 4460046 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 5.1463. Min Range: -5.1463

Max Act: 5.0537. Min Act: -0.1700

Data Index: 1003405 (Open Web Text)

Max Activating Token Index: 258

Text #5

Max Range: 5.1463. Min Range: -5.1463

Max Act: 5.0033. Min Act: -0.1700

Data Index: 7417782 (Open Web Text)

Max Activating Token Index: 583

Text #6

Max Range: 5.1463. Min Range: -5.1463

Max Act: 5.0078. Min Act: -0.1700

Data Index: 5510849 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 5.1463. Min Range: -5.1463

Max Act: 5.0204. Min Act: -0.1700

Data Index: 2462975 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 5.1463. Min Range: -5.1463

Max Act: 5.0387. Min Act: -0.1700

Data Index: 6570341 (Open Web Text)

Max Activating Token Index: 589

Text #9

Max Range: 5.1463. Min Range: -5.1463

Max Act: 5.0044. Min Act: -0.1700

Data Index: 890454 (Open Web Text)

Max Activating Token Index: 566

Text #10

Max Range: 5.1463. Min Range: -5.1463

Max Act: 4.9929. Min Act: -0.1700

Data Index: 6245638 (Open Web Text)

Max Activating Token Index: 665

Text #11

Max Range: 5.1463. Min Range: -5.1463

Max Act: 5.0306. Min Act: -0.1700

Data Index: 6343165 (Open Web Text)

Max Activating Token Index: 582

Text #12

Max Range: 5.1463. Min Range: -5.1463

Max Act: 4.9470. Min Act: -0.1700

Data Index: 3538569 (Open Web Text)

Max Activating Token Index: 812

Text #13

Max Range: 5.1463. Min Range: -5.1463

Max Act: 4.9748. Min Act: -0.1700

Data Index: 929079 (Open Web Text)

Max Activating Token Index: 164

Text #14

Max Range: 5.1463. Min Range: -5.1463

Max Act: 4.9537. Min Act: -0.1700

Data Index: 725819 (Open Web Text)

Max Activating Token Index: 90

Text #15

Max Range: 5.1463. Min Range: -5.1463

Max Act: 4.9650. Min Act: -0.1700

Data Index: 6868106 (Open Web Text)

Max Activating Token Index: 332

Text #16

Max Range: 5.1463. Min Range: -5.1463

Max Act: 4.9253. Min Act: -0.1700

Data Index: 6227891 (Open Web Text)

Max Activating Token Index: 491

Text #17

Max Range: 5.1463. Min Range: -5.1463

Max Act: 4.9301. Min Act: -0.1700

Data Index: 6191788 (Open Web Text)

Max Activating Token Index: 666

Text #18

Max Range: 5.1463. Min Range: -5.1463

Max Act: 4.9128. Min Act: -0.1700

Data Index: 4316596 (Open Web Text)

Max Activating Token Index: 722

Text #19

Max Range: 5.1463. Min Range: -5.1463

Max Act: 4.9184. Min Act: -0.1700

Data Index: 2678093 (Open Web Text)

Max Activating Token Index: 55