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

Dataset: Open Web Text

Neuron 2358 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: 3.0437. Min Range: -3.0437

Max Act: 3.0437. Min Act: -0.1700

Data Index: 8419236 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 3.0437. Min Range: -3.0437

Max Act: 3.0118. Min Act: -0.1700

Data Index: 6223169 (Open Web Text)

Max Activating Token Index: 728

Text #2

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.9580. Min Act: -0.1700

Data Index: 7872501 (Open Web Text)

Max Activating Token Index: 577

Text #3

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.9318. Min Act: -0.1700

Data Index: 2860074 (Open Web Text)

Max Activating Token Index: 662

Text #4

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.9047. Min Act: -0.1700

Data Index: 3769892 (Open Web Text)

Max Activating Token Index: 148

Text #5

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8723. Min Act: -0.1700

Data Index: 3147154 (Open Web Text)

Max Activating Token Index: 743

Text #6

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8903. Min Act: -0.1700

Data Index: 3797716 (Open Web Text)

Max Activating Token Index: 558

Text #7

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8700. Min Act: -0.1700

Data Index: 5366215 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8398. Min Act: -0.1700

Data Index: 6347199 (Open Web Text)

Max Activating Token Index: 930

Text #9

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8610. Min Act: -0.1700

Data Index: 1841865 (Open Web Text)

Max Activating Token Index: 981

Text #10

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8650. Min Act: -0.1700

Data Index: 2833977 (Open Web Text)

Max Activating Token Index: 521

Text #11

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8377. Min Act: -0.1700

Data Index: 351495 (Open Web Text)

Max Activating Token Index: 780

Text #12

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8310. Min Act: -0.1700

Data Index: 5961994 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8171. Min Act: -0.1700

Data Index: 3106656 (Open Web Text)

Max Activating Token Index: 570

Text #14

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8293. Min Act: -0.1700

Data Index: 8161943 (Open Web Text)

Max Activating Token Index: 419

Text #15

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.7896. Min Act: -0.1700

Data Index: 1464644 (Open Web Text)

Max Activating Token Index: 720

Text #16

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8490. Min Act: -0.1700

Data Index: 1514917 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8170. Min Act: -0.1700

Data Index: 8776375 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8373. Min Act: -0.1700

Data Index: 2745152 (Open Web Text)

Max Activating Token Index: 204

Text #19

Max Range: 3.0437. Min Range: -3.0437

Max Act: 2.8005. Min Act: -0.1700

Data Index: 1550066 (Open Web Text)

Max Activating Token Index: 95