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

Dataset: Open Web Text

Neuron 2773 in Layer 2

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: 5.3544. Min Range: -5.3544

Max Act: 5.3544. Min Act: -0.1700

Data Index: 2796089 (Open Web Text)

Max Activating Token Index: 784

Text #1

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.3368. Min Act: -0.1700

Data Index: 7426580 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.3206. Min Act: -0.1700

Data Index: 1490328 (Open Web Text)

Max Activating Token Index: 436

Text #3

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2532. Min Act: -0.1700

Data Index: 6707772 (Open Web Text)

Max Activating Token Index: 912

Text #4

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2678. Min Act: -0.1700

Data Index: 7231091 (Open Web Text)

Max Activating Token Index: 539

Text #5

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2349. Min Act: -0.1700

Data Index: 658398 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2298. Min Act: -0.1700

Data Index: 214943 (Open Web Text)

Max Activating Token Index: 865

Text #7

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2429. Min Act: -0.1700

Data Index: 4629566 (Open Web Text)

Max Activating Token Index: 428

Text #8

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2488. Min Act: -0.1700

Data Index: 8146356 (Open Web Text)

Max Activating Token Index: 824

Text #9

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2253. Min Act: -0.1700

Data Index: 7783246 (Open Web Text)

Max Activating Token Index: 862

Text #10

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2411. Min Act: -0.1700

Data Index: 2301645 (Open Web Text)

Max Activating Token Index: 575

Text #11

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1926. Min Act: -0.1700

Data Index: 7105179 (Open Web Text)

Max Activating Token Index: 838

Text #12

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2238. Min Act: -0.1700

Data Index: 2450339 (Open Web Text)

Max Activating Token Index: 588

Text #13

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1698. Min Act: -0.1698

Data Index: 5549481 (Open Web Text)

Max Activating Token Index: 764

Text #14

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.2024. Min Act: -0.1700

Data Index: 7275944 (Open Web Text)

Max Activating Token Index: 169

Text #15

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1990. Min Act: -0.1700

Data Index: 6870937 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1786. Min Act: -0.1700

Data Index: 1817836 (Open Web Text)

Max Activating Token Index: 731

Text #17

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1806. Min Act: -0.1700

Data Index: 736547 (Open Web Text)

Max Activating Token Index: 171

Text #18

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1720. Min Act: -0.1700

Data Index: 6196045 (Open Web Text)

Max Activating Token Index: 588

Text #19

Max Range: 5.3544. Min Range: -5.3544

Max Act: 5.1459. Min Act: -0.1700

Data Index: 7213240 (Open Web Text)

Max Activating Token Index: 713