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

Dataset: Open Web Text

Neuron 482 in Layer 2

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: 3.8484. Min Range: -3.8484

Max Act: 3.8484. Min Act: -0.1700

Data Index: 6973657 (Open Web Text)

Max Activating Token Index: 152

Text #1

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.8250. Min Act: -0.1700

Data Index: 6608451 (Open Web Text)

Max Activating Token Index: 58

Text #2

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.8210. Min Act: -0.1700

Data Index: 618729 (Open Web Text)

Max Activating Token Index: 348

Text #3

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7650. Min Act: -0.1700

Data Index: 2493488 (Open Web Text)

Max Activating Token Index: 587

Text #4

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7434. Min Act: -0.1700

Data Index: 600037 (Open Web Text)

Max Activating Token Index: 897

Text #5

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7403. Min Act: -0.1700

Data Index: 2094893 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7527. Min Act: -0.1700

Data Index: 5241816 (Open Web Text)

Max Activating Token Index: 497

Text #7

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7438. Min Act: -0.1700

Data Index: 7500391 (Open Web Text)

Max Activating Token Index: 402

Text #8

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6841. Min Act: -0.1700

Data Index: 8032426 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6915. Min Act: -0.1700

Data Index: 5779826 (Open Web Text)

Max Activating Token Index: 377

Text #10

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6915. Min Act: -0.1700

Data Index: 5428063 (Open Web Text)

Max Activating Token Index: 380

Text #11

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6933. Min Act: -0.1700

Data Index: 712526 (Open Web Text)

Max Activating Token Index: 281

Text #12

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7244. Min Act: -0.1700

Data Index: 7822070 (Open Web Text)

Max Activating Token Index: 924

Text #13

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7186. Min Act: -0.1700

Data Index: 5040786 (Open Web Text)

Max Activating Token Index: 723

Text #14

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6944. Min Act: -0.1700

Data Index: 7757019 (Open Web Text)

Max Activating Token Index: 978

Text #15

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6879. Min Act: -0.1700

Data Index: 4995564 (Open Web Text)

Max Activating Token Index: 727

Text #16

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7094. Min Act: -0.1700

Data Index: 7038474 (Open Web Text)

Max Activating Token Index: 754

Text #17

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7038. Min Act: -0.1700

Data Index: 2734250 (Open Web Text)

Max Activating Token Index: 186

Text #18

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7146. Min Act: -0.1700

Data Index: 6524266 (Open Web Text)

Max Activating Token Index: 817

Text #19

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6902. Min Act: -0.1700

Data Index: 3289978 (Open Web Text)

Max Activating Token Index: 825