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

Dataset: Open Web Text

Neuron 1180 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: 3.9419. Min Range: -3.9419

Max Act: 3.9419. Min Act: -0.1700

Data Index: 6377620 (Open Web Text)

Max Activating Token Index: 979

Text #1

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.9101. Min Act: -0.1700

Data Index: 3339804 (Open Web Text)

Max Activating Token Index: 420

Text #2

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.9237. Min Act: -0.1700

Data Index: 4580639 (Open Web Text)

Max Activating Token Index: 502

Text #3

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.8491. Min Act: -0.1700

Data Index: 8826740 (Open Web Text)

Max Activating Token Index: 422

Text #4

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.8754. Min Act: -0.1700

Data Index: 1196206 (Open Web Text)

Max Activating Token Index: 887

Text #5

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.8279. Min Act: -0.1700

Data Index: 6658950 (Open Web Text)

Max Activating Token Index: 808

Text #6

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.8298. Min Act: -0.1700

Data Index: 3793487 (Open Web Text)

Max Activating Token Index: 151

Text #7

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.7961. Min Act: -0.1700

Data Index: 7171652 (Open Web Text)

Max Activating Token Index: 962

Text #8

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.7800. Min Act: -0.1700

Data Index: 3820682 (Open Web Text)

Max Activating Token Index: 562

Text #9

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.7280. Min Act: -0.1700

Data Index: 7143759 (Open Web Text)

Max Activating Token Index: 546

Text #10

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.7299. Min Act: -0.1700

Data Index: 5578485 (Open Web Text)

Max Activating Token Index: 625

Text #11

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.6925. Min Act: -0.1700

Data Index: 6584227 (Open Web Text)

Max Activating Token Index: 769

Text #12

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.6667. Min Act: -0.1700

Data Index: 1520930 (Open Web Text)

Max Activating Token Index: 943

Text #13

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.6883. Min Act: -0.1700

Data Index: 4558618 (Open Web Text)

Max Activating Token Index: 138

Text #14

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.6909. Min Act: -0.1700

Data Index: 5184857 (Open Web Text)

Max Activating Token Index: 562

Text #15

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.6491. Min Act: -0.1700

Data Index: 3471650 (Open Web Text)

Max Activating Token Index: 1013

Text #16

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.6511. Min Act: -0.1700

Data Index: 2727758 (Open Web Text)

Max Activating Token Index: 769

Text #17

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.6539. Min Act: -0.1700

Data Index: 7123323 (Open Web Text)

Max Activating Token Index: 463

Text #18

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.6452. Min Act: -0.1700

Data Index: 7886540 (Open Web Text)

Max Activating Token Index: 871

Text #19

Max Range: 3.9419. Min Range: -3.9419

Max Act: 3.6524. Min Act: -0.1700

Data Index: 4348123 (Open Web Text)

Max Activating Token Index: 913