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

Dataset: Open Web Text

Neuron 477 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: 0.6554. Min Range: -0.6554

Max Act: 0.6489. Min Act: -0.1700

Data Index: 2377248 (Open Web Text)

Max Activating Token Index: 614

Text #1

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6554. Min Act: -0.1700

Data Index: 2763663 (Open Web Text)

Max Activating Token Index: 633

Text #2

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6537. Min Act: -0.1700

Data Index: 7028413 (Open Web Text)

Max Activating Token Index: 614

Text #3

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6502. Min Act: -0.1700

Data Index: 8809365 (Open Web Text)

Max Activating Token Index: 627

Text #4

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6374. Min Act: -0.1700

Data Index: 3423818 (Open Web Text)

Max Activating Token Index: 632

Text #5

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6378. Min Act: -0.1700

Data Index: 3563227 (Open Web Text)

Max Activating Token Index: 610

Text #6

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6430. Min Act: -0.1700

Data Index: 3779886 (Open Web Text)

Max Activating Token Index: 608

Text #7

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6327. Min Act: -0.1700

Data Index: 3208764 (Open Web Text)

Max Activating Token Index: 618

Text #8

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6374. Min Act: -0.1700

Data Index: 5569218 (Open Web Text)

Max Activating Token Index: 612

Text #9

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6346. Min Act: -0.1700

Data Index: 2100123 (Open Web Text)

Max Activating Token Index: 631

Text #10

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6239. Min Act: -0.1700

Data Index: 1752322 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6299. Min Act: -0.1700

Data Index: 2923373 (Open Web Text)

Max Activating Token Index: 611

Text #12

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6350. Min Act: -0.1700

Data Index: 4915474 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6296. Min Act: -0.1700

Data Index: 310197 (Open Web Text)

Max Activating Token Index: 621

Text #14

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6289. Min Act: -0.1700

Data Index: 1877835 (Open Web Text)

Max Activating Token Index: 626

Text #15

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6254. Min Act: -0.1700

Data Index: 4277620 (Open Web Text)

Max Activating Token Index: 622

Text #16

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6348. Min Act: -0.1700

Data Index: 4211852 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6323. Min Act: -0.1700

Data Index: 1482063 (Open Web Text)

Max Activating Token Index: 637

Text #18

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6275. Min Act: -0.1700

Data Index: 2703831 (Open Web Text)

Max Activating Token Index: 631

Text #19

Max Range: 0.6554. Min Range: -0.6554

Max Act: 0.6390. Min Act: -0.1700

Data Index: 896451 (Open Web Text)

Max Activating Token Index: 624