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

Dataset: Open Web Text

Neuron 621 in Layer 5

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: 3.2254. Min Range: -3.2254

Max Act: 3.2254. Min Act: -0.1700

Data Index: 6864430 (Open Web Text)

Max Activating Token Index: 546

Text #1

Max Range: 3.2254. Min Range: -3.2254

Max Act: 3.1702. Min Act: -0.1700

Data Index: 5669660 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 3.2254. Min Range: -3.2254

Max Act: 3.1350. Min Act: -0.1700

Data Index: 413203 (Open Web Text)

Max Activating Token Index: 678

Text #3

Max Range: 3.2254. Min Range: -3.2254

Max Act: 3.1346. Min Act: -0.1700

Data Index: 8351498 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 3.2254. Min Range: -3.2254

Max Act: 3.1666. Min Act: -0.1700

Data Index: 3546360 (Open Web Text)

Max Activating Token Index: 454

Text #5

Max Range: 3.2254. Min Range: -3.2254

Max Act: 3.0732. Min Act: -0.1700

Data Index: 2243063 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 3.2254. Min Range: -3.2254

Max Act: 3.0170. Min Act: -0.1700

Data Index: 6312601 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 3.2254. Min Range: -3.2254

Max Act: 3.0123. Min Act: -0.1700

Data Index: 784850 (Open Web Text)

Max Activating Token Index: 965

Text #8

Max Range: 3.2254. Min Range: -3.2254

Max Act: 3.0019. Min Act: -0.1700

Data Index: 685042 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 3.2254. Min Range: -3.2254

Max Act: 3.0229. Min Act: -0.1700

Data Index: 8593377 (Open Web Text)

Max Activating Token Index: 541

Text #10

Max Range: 3.2254. Min Range: -3.2254

Max Act: 2.9813. Min Act: -0.1700

Data Index: 6032714 (Open Web Text)

Max Activating Token Index: 683

Text #11

Max Range: 3.2254. Min Range: -3.2254

Max Act: 2.9653. Min Act: -0.1700

Data Index: 820648 (Open Web Text)

Max Activating Token Index: 931

Text #12

Max Range: 3.2254. Min Range: -3.2254

Max Act: 2.9494. Min Act: -0.1700

Data Index: 7533777 (Open Web Text)

Max Activating Token Index: 884

Text #13

Max Range: 3.2254. Min Range: -3.2254

Max Act: 2.9506. Min Act: -0.1700

Data Index: 3824112 (Open Web Text)

Max Activating Token Index: 714

Text #14

Max Range: 3.2254. Min Range: -3.2254

Max Act: 2.9432. Min Act: -0.1700

Data Index: 6101650 (Open Web Text)

Max Activating Token Index: 508

Text #15

Max Range: 3.2254. Min Range: -3.2254

Max Act: 2.9243. Min Act: -0.1700

Data Index: 539896 (Open Web Text)

Max Activating Token Index: 395

Text #16

Max Range: 3.2254. Min Range: -3.2254

Max Act: 2.9475. Min Act: -0.1700

Data Index: 846931 (Open Web Text)

Max Activating Token Index: 284

Text #17

Max Range: 3.2254. Min Range: -3.2254

Max Act: 2.9068. Min Act: -0.1700

Data Index: 7950096 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 3.2254. Min Range: -3.2254

Max Act: 2.9327. Min Act: -0.1700

Data Index: 6935137 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 3.2254. Min Range: -3.2254

Max Act: 2.9261. Min Act: -0.1700

Data Index: 7220525 (Open Web Text)

Max Activating Token Index: 694