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

Dataset: Open Web Text

Neuron 672 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: 1.4329. Min Range: -1.4329

Max Act: 1.4329. Min Act: -0.1700

Data Index: 7893349 (Open Web Text)

Max Activating Token Index: 646

Text #1

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3805. Min Act: -0.1695

Data Index: 2939853 (Open Web Text)

Max Activating Token Index: 162

Text #2

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3720. Min Act: -0.1700

Data Index: 2743349 (Open Web Text)

Max Activating Token Index: 477

Text #3

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3540. Min Act: -0.1699

Data Index: 5206730 (Open Web Text)

Max Activating Token Index: 993

Text #4

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3530. Min Act: -0.1698

Data Index: 1077655 (Open Web Text)

Max Activating Token Index: 137

Text #5

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3465. Min Act: -0.1700

Data Index: 8539009 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3380. Min Act: -0.1697

Data Index: 4702468 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3446. Min Act: -0.1700

Data Index: 6881078 (Open Web Text)

Max Activating Token Index: 666

Text #8

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3410. Min Act: -0.1698

Data Index: 71659 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3335. Min Act: -0.1700

Data Index: 4258771 (Open Web Text)

Max Activating Token Index: 571

Text #10

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3379. Min Act: -0.1695

Data Index: 1109870 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3290. Min Act: -0.1700

Data Index: 8417063 (Open Web Text)

Max Activating Token Index: 401

Text #12

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3248. Min Act: -0.1695

Data Index: 2443185 (Open Web Text)

Max Activating Token Index: 818

Text #13

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3198. Min Act: -0.1699

Data Index: 5455167 (Open Web Text)

Max Activating Token Index: 746

Text #14

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3273. Min Act: -0.1700

Data Index: 5284918 (Open Web Text)

Max Activating Token Index: 239

Text #15

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3193. Min Act: -0.1700

Data Index: 7773477 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3212. Min Act: -0.1700

Data Index: 7231744 (Open Web Text)

Max Activating Token Index: 738

Text #17

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3300. Min Act: -0.1680

Data Index: 6444729 (Open Web Text)

Max Activating Token Index: 999

Text #18

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3131. Min Act: -0.1700

Data Index: 5609659 (Open Web Text)

Max Activating Token Index: 652

Text #19

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3175. Min Act: -0.1698

Data Index: 4980509 (Open Web Text)

Max Activating Token Index: 1014