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

Dataset: Open Web Text

Neuron 2160 in Layer 1

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: 1.8385. Min Range: -1.8385

Max Act: 1.8385. Min Act: -0.1700

Data Index: 7028546 (Open Web Text)

Max Activating Token Index: 588

Text #1

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.8234. Min Act: -0.1700

Data Index: 8507079 (Open Web Text)

Max Activating Token Index: 617

Text #2

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.8136. Min Act: -0.1700

Data Index: 6745835 (Open Web Text)

Max Activating Token Index: 967

Text #3

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7945. Min Act: -0.1700

Data Index: 2892811 (Open Web Text)

Max Activating Token Index: 495

Text #4

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7919. Min Act: -0.1700

Data Index: 8832048 (Open Web Text)

Max Activating Token Index: 363

Text #5

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.8027. Min Act: -0.1689

Data Index: 5542073 (Open Web Text)

Max Activating Token Index: 386

Text #6

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7924. Min Act: -0.1700

Data Index: 4499568 (Open Web Text)

Max Activating Token Index: 486

Text #7

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7953. Min Act: -0.1627

Data Index: 2321985 (Open Web Text)

Max Activating Token Index: 140

Text #8

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7859. Min Act: -0.1700

Data Index: 900786 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7894. Min Act: -0.1700

Data Index: 7755334 (Open Web Text)

Max Activating Token Index: 869

Text #10

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7804. Min Act: -0.1700

Data Index: 3125844 (Open Web Text)

Max Activating Token Index: 602

Text #11

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7787. Min Act: -0.1700

Data Index: 6757131 (Open Web Text)

Max Activating Token Index: 71

Text #12

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7782. Min Act: -0.1700

Data Index: 863813 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7697. Min Act: -0.1700

Data Index: 8505868 (Open Web Text)

Max Activating Token Index: 650

Text #14

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7697. Min Act: -0.1700

Data Index: 8382778 (Open Web Text)

Max Activating Token Index: 624

Text #15

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7793. Min Act: -0.1700

Data Index: 1848043 (Open Web Text)

Max Activating Token Index: 513

Text #16

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7712. Min Act: -0.1699

Data Index: 6543617 (Open Web Text)

Max Activating Token Index: 483

Text #17

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7663. Min Act: -0.1700

Data Index: 4827928 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7719. Min Act: -0.1700

Data Index: 3060986 (Open Web Text)

Max Activating Token Index: 452

Text #19

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7643. Min Act: -0.1699

Data Index: 2753422 (Open Web Text)

Max Activating Token Index: 50