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

Dataset: Open Web Text

Neuron 943 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: 3.7412. Min Range: -3.7412

Max Act: 3.7412. Min Act: -0.1700

Data Index: 7613423 (Open Web Text)

Max Activating Token Index: 881

Text #1

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.7334. Min Act: -0.1700

Data Index: 2241961 (Open Web Text)

Max Activating Token Index: 651

Text #2

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.7192. Min Act: -0.1700

Data Index: 1499522 (Open Web Text)

Max Activating Token Index: 727

Text #3

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.7335. Min Act: -0.1700

Data Index: 5811353 (Open Web Text)

Max Activating Token Index: 869

Text #4

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.7061. Min Act: -0.1700

Data Index: 4897519 (Open Web Text)

Max Activating Token Index: 96

Text #5

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6871. Min Act: -0.1700

Data Index: 750742 (Open Web Text)

Max Activating Token Index: 298

Text #6

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6736. Min Act: -0.1700

Data Index: 8003671 (Open Web Text)

Max Activating Token Index: 864

Text #7

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.7036. Min Act: -0.1700

Data Index: 1035926 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6856. Min Act: -0.1700

Data Index: 3783796 (Open Web Text)

Max Activating Token Index: 368

Text #9

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6793. Min Act: -0.1700

Data Index: 1262403 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6701. Min Act: -0.1700

Data Index: 4368166 (Open Web Text)

Max Activating Token Index: 457

Text #11

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6429. Min Act: -0.1700

Data Index: 8280880 (Open Web Text)

Max Activating Token Index: 182

Text #12

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6535. Min Act: -0.1700

Data Index: 3904447 (Open Web Text)

Max Activating Token Index: 663

Text #13

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6570. Min Act: -0.1700

Data Index: 1810636 (Open Web Text)

Max Activating Token Index: 357

Text #14

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6728. Min Act: -0.1700

Data Index: 3243980 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6649. Min Act: -0.1700

Data Index: 5153924 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6583. Min Act: -0.1700

Data Index: 3103075 (Open Web Text)

Max Activating Token Index: 1010

Text #17

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6529. Min Act: -0.1700

Data Index: 2913111 (Open Web Text)

Max Activating Token Index: 856

Text #18

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6713. Min Act: -0.1700

Data Index: 823333 (Open Web Text)

Max Activating Token Index: 826

Text #19

Max Range: 3.7412. Min Range: -3.7412

Max Act: 3.6265. Min Act: -0.1700

Data Index: 410495 (Open Web Text)

Max Activating Token Index: 769