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

Dataset: Open Web Text

Neuron 1668 in Layer 5

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: 2.1543. Min Range: -2.1543

Max Act: 2.1543. Min Act: -0.1700

Data Index: 2088027 (Open Web Text)

Max Activating Token Index: 790

Text #1

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.1280. Min Act: -0.1700

Data Index: 1836004 (Open Web Text)

Max Activating Token Index: 358

Text #2

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.1246. Min Act: -0.1700

Data Index: 1321797 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0884. Min Act: -0.1700

Data Index: 4979276 (Open Web Text)

Max Activating Token Index: 929

Text #4

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0988. Min Act: -0.1700

Data Index: 4437599 (Open Web Text)

Max Activating Token Index: 294

Text #5

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0720. Min Act: -0.1700

Data Index: 8730977 (Open Web Text)

Max Activating Token Index: 919

Text #6

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0862. Min Act: -0.1700

Data Index: 1646751 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0868. Min Act: -0.1700

Data Index: 1582491 (Open Web Text)

Max Activating Token Index: 401

Text #8

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0569. Min Act: -0.1700

Data Index: 8416154 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0482. Min Act: -0.1700

Data Index: 6808879 (Open Web Text)

Max Activating Token Index: 269

Text #10

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0617. Min Act: -0.1700

Data Index: 149809 (Open Web Text)

Max Activating Token Index: 719

Text #11

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0454. Min Act: -0.1700

Data Index: 4582606 (Open Web Text)

Max Activating Token Index: 602

Text #12

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0488. Min Act: -0.1700

Data Index: 4697511 (Open Web Text)

Max Activating Token Index: 114

Text #13

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0562. Min Act: -0.1700

Data Index: 7475424 (Open Web Text)

Max Activating Token Index: 929

Text #14

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0437. Min Act: -0.1700

Data Index: 4290945 (Open Web Text)

Max Activating Token Index: 713

Text #15

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0428. Min Act: -0.1700

Data Index: 2625887 (Open Web Text)

Max Activating Token Index: 847

Text #16

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0470. Min Act: -0.1700

Data Index: 488926 (Open Web Text)

Max Activating Token Index: 262

Text #17

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0231. Min Act: -0.1700

Data Index: 2926726 (Open Web Text)

Max Activating Token Index: 689

Text #18

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0303. Min Act: -0.1700

Data Index: 1953579 (Open Web Text)

Max Activating Token Index: 117

Text #19

Max Range: 2.1543. Min Range: -2.1543

Max Act: 2.0267. Min Act: -0.1700

Data Index: 1820385 (Open Web Text)

Max Activating Token Index: 719