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

Dataset: Open Web Text

Neuron 657 in Layer 6

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: 3.1425. Min Range: -3.1425

Max Act: 3.1425. Min Act: -0.1700

Data Index: 5713949 (Open Web Text)

Max Activating Token Index: 196

Text #1

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.9122. Min Act: -0.1700

Data Index: 3901933 (Open Web Text)

Max Activating Token Index: 843

Text #2

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.9041. Min Act: -0.1700

Data Index: 1347030 (Open Web Text)

Max Activating Token Index: 920

Text #3

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8599. Min Act: -0.1700

Data Index: 7037031 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8402. Min Act: -0.1700

Data Index: 5074991 (Open Web Text)

Max Activating Token Index: 311

Text #5

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8261. Min Act: -0.1700

Data Index: 6339602 (Open Web Text)

Max Activating Token Index: 764

Text #6

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8669. Min Act: -0.1700

Data Index: 3370558 (Open Web Text)

Max Activating Token Index: 884

Text #7

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8483. Min Act: -0.1700

Data Index: 4593108 (Open Web Text)

Max Activating Token Index: 528

Text #8

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8398. Min Act: -0.1700

Data Index: 3938507 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8402. Min Act: -0.1700

Data Index: 6692521 (Open Web Text)

Max Activating Token Index: 711

Text #10

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8156. Min Act: -0.1700

Data Index: 5418230 (Open Web Text)

Max Activating Token Index: 837

Text #11

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.7881. Min Act: -0.1700

Data Index: 1516839 (Open Web Text)

Max Activating Token Index: 836

Text #12

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8164. Min Act: -0.1700

Data Index: 6930748 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8002. Min Act: -0.1700

Data Index: 4756224 (Open Web Text)

Max Activating Token Index: 342

Text #14

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8014. Min Act: -0.1700

Data Index: 4590701 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.7896. Min Act: -0.1700

Data Index: 7323397 (Open Web Text)

Max Activating Token Index: 379

Text #16

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.7980. Min Act: -0.1700

Data Index: 7815922 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.7824. Min Act: -0.1700

Data Index: 127538 (Open Web Text)

Max Activating Token Index: 764

Text #18

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.8012. Min Act: -0.1700

Data Index: 6974943 (Open Web Text)

Max Activating Token Index: 460

Text #19

Max Range: 3.1425. Min Range: -3.1425

Max Act: 2.7553. Min Act: -0.1700

Data Index: 4221880 (Open Web Text)

Max Activating Token Index: 680