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

Dataset: Open Web Text

Neuron 1696 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: 3.5909. Min Range: -3.5909

Max Act: 3.5909. Min Act: -0.1700

Data Index: 1306428 (Open Web Text)

Max Activating Token Index: 181

Text #1

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.5553. Min Act: -0.1700

Data Index: 4020083 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.5282. Min Act: -0.1700

Data Index: 6632131 (Open Web Text)

Max Activating Token Index: 843

Text #3

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.5433. Min Act: -0.1700

Data Index: 5796301 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4913. Min Act: -0.1700

Data Index: 6891904 (Open Web Text)

Max Activating Token Index: 67

Text #5

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4873. Min Act: -0.1700

Data Index: 4309550 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4557. Min Act: -0.1700

Data Index: 8472829 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4462. Min Act: -0.1700

Data Index: 2154439 (Open Web Text)

Max Activating Token Index: 97

Text #8

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4275. Min Act: -0.1700

Data Index: 1966105 (Open Web Text)

Max Activating Token Index: 992

Text #9

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4567. Min Act: -0.1700

Data Index: 8821606 (Open Web Text)

Max Activating Token Index: 773

Text #10

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4422. Min Act: -0.1700

Data Index: 8802882 (Open Web Text)

Max Activating Token Index: 990

Text #11

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4234. Min Act: -0.1700

Data Index: 1606711 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4781. Min Act: -0.1700

Data Index: 8028173 (Open Web Text)

Max Activating Token Index: 669

Text #13

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4603. Min Act: -0.1700

Data Index: 7985382 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4484. Min Act: -0.1700

Data Index: 7543774 (Open Web Text)

Max Activating Token Index: 636

Text #15

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4465. Min Act: -0.1700

Data Index: 1464210 (Open Web Text)

Max Activating Token Index: 956

Text #16

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4052. Min Act: -0.1700

Data Index: 5973072 (Open Web Text)

Max Activating Token Index: 658

Text #17

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4208. Min Act: -0.1700

Data Index: 6063630 (Open Web Text)

Max Activating Token Index: 603

Text #18

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4146. Min Act: -0.1700

Data Index: 6481517 (Open Web Text)

Max Activating Token Index: 81

Text #19

Max Range: 3.5909. Min Range: -3.5909

Max Act: 3.4340. Min Act: -0.1700

Data Index: 6622394 (Open Web Text)

Max Activating Token Index: 744