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

Dataset: Open Web Text

Neuron 8 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: 4.0670. Min Range: -4.0670

Max Act: 4.0670. Min Act: -0.1700

Data Index: 3002639 (Open Web Text)

Max Activating Token Index: 593

Text #1

Max Range: 4.0670. Min Range: -4.0670

Max Act: 4.0587. Min Act: -0.1700

Data Index: 3498546 (Open Web Text)

Max Activating Token Index: 777

Text #2

Max Range: 4.0670. Min Range: -4.0670

Max Act: 4.0455. Min Act: -0.1700

Data Index: 1559572 (Open Web Text)

Max Activating Token Index: 243

Text #3

Max Range: 4.0670. Min Range: -4.0670

Max Act: 4.0170. Min Act: -0.1700

Data Index: 7228046 (Open Web Text)

Max Activating Token Index: 350

Text #4

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.9956. Min Act: -0.1700

Data Index: 3018713 (Open Web Text)

Max Activating Token Index: 714

Text #5

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.9012. Min Act: -0.1700

Data Index: 2660038 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.9301. Min Act: -0.1700

Data Index: 40943 (Open Web Text)

Max Activating Token Index: 696

Text #7

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.9105. Min Act: -0.1700

Data Index: 6003348 (Open Web Text)

Max Activating Token Index: 785

Text #8

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.8739. Min Act: -0.1700

Data Index: 6403889 (Open Web Text)

Max Activating Token Index: 711

Text #9

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.8654. Min Act: -0.1700

Data Index: 7740073 (Open Web Text)

Max Activating Token Index: 955

Text #10

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.8685. Min Act: -0.1700

Data Index: 1200216 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.8334. Min Act: -0.1700

Data Index: 1948561 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.8565. Min Act: -0.1700

Data Index: 5680733 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.8095. Min Act: -0.1700

Data Index: 8767699 (Open Web Text)

Max Activating Token Index: 567

Text #14

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.8064. Min Act: -0.1700

Data Index: 4189761 (Open Web Text)

Max Activating Token Index: 864

Text #15

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.8419. Min Act: -0.1700

Data Index: 152686 (Open Web Text)

Max Activating Token Index: 499

Text #16

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.8198. Min Act: -0.1700

Data Index: 2951761 (Open Web Text)

Max Activating Token Index: 571

Text #17

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.8329. Min Act: -0.1700

Data Index: 2545181 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.7907. Min Act: -0.1700

Data Index: 2052885 (Open Web Text)

Max Activating Token Index: 165

Text #19

Max Range: 4.0670. Min Range: -4.0670

Max Act: 3.7968. Min Act: -0.1700

Data Index: 4745102 (Open Web Text)

Max Activating Token Index: 980