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

Dataset: Open Web Text

Neuron 348 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: 4.0885. Min Range: -4.0885

Max Act: 4.0885. Min Act: -0.1700

Data Index: 4300206 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.9816. Min Act: -0.1700

Data Index: 8357408 (Open Web Text)

Max Activating Token Index: 723

Text #2

Max Range: 4.0885. Min Range: -4.0885

Max Act: 4.0190. Min Act: -0.1700

Data Index: 574837 (Open Web Text)

Max Activating Token Index: 721

Text #3

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.9446. Min Act: -0.1700

Data Index: 3195709 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.9235. Min Act: -0.1700

Data Index: 7862697 (Open Web Text)

Max Activating Token Index: 683

Text #5

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.9330. Min Act: -0.1700

Data Index: 2436453 (Open Web Text)

Max Activating Token Index: 365

Text #6

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.9370. Min Act: -0.1700

Data Index: 2410381 (Open Web Text)

Max Activating Token Index: 592

Text #7

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.9265. Min Act: -0.1700

Data Index: 5917714 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.9292. Min Act: -0.1700

Data Index: 146057 (Open Web Text)

Max Activating Token Index: 96

Text #9

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.9448. Min Act: -0.1700

Data Index: 2124984 (Open Web Text)

Max Activating Token Index: 827

Text #10

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.9495. Min Act: -0.1700

Data Index: 8386355 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.8967. Min Act: -0.1700

Data Index: 2312441 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.9061. Min Act: -0.1700

Data Index: 1392782 (Open Web Text)

Max Activating Token Index: 858

Text #13

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.8834. Min Act: -0.1700

Data Index: 350559 (Open Web Text)

Max Activating Token Index: 619

Text #14

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.8989. Min Act: -0.1700

Data Index: 1254276 (Open Web Text)

Max Activating Token Index: 323

Text #15

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.8619. Min Act: -0.1700

Data Index: 2360973 (Open Web Text)

Max Activating Token Index: 772

Text #16

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.8366. Min Act: -0.1700

Data Index: 6849283 (Open Web Text)

Max Activating Token Index: 505

Text #17

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.8908. Min Act: -0.1700

Data Index: 1608949 (Open Web Text)

Max Activating Token Index: 747

Text #18

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.8625. Min Act: -0.1700

Data Index: 3911244 (Open Web Text)

Max Activating Token Index: 389

Text #19

Max Range: 4.0885. Min Range: -4.0885

Max Act: 3.8499. Min Act: -0.1700

Data Index: 445467 (Open Web Text)

Max Activating Token Index: 599