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

Dataset: Open Web Text

Neuron 2538 in Layer 6

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: 5.2357. Min Range: -5.2357

Max Act: 5.2357. Min Act: -0.1690

Data Index: 1519852 (Open Web Text)

Max Activating Token Index: 357

Text #1

Max Range: 5.2357. Min Range: -5.2357

Max Act: 5.1478. Min Act: -0.1700

Data Index: 4999520 (Open Web Text)

Max Activating Token Index: 893

Text #2

Max Range: 5.2357. Min Range: -5.2357

Max Act: 5.0843. Min Act: -0.1700

Data Index: 6775076 (Open Web Text)

Max Activating Token Index: 984

Text #3

Max Range: 5.2357. Min Range: -5.2357

Max Act: 5.1259. Min Act: -0.1700

Data Index: 7499814 (Open Web Text)

Max Activating Token Index: 934

Text #4

Max Range: 5.2357. Min Range: -5.2357

Max Act: 5.0349. Min Act: -0.1699

Data Index: 881841 (Open Web Text)

Max Activating Token Index: 601

Text #5

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9887. Min Act: -0.1700

Data Index: 3956088 (Open Web Text)

Max Activating Token Index: 190

Text #6

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9846. Min Act: -0.1700

Data Index: 8189585 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9903. Min Act: -0.1675

Data Index: 1169533 (Open Web Text)

Max Activating Token Index: 569

Text #8

Max Range: 5.2357. Min Range: -5.2357

Max Act: 5.0281. Min Act: -0.1699

Data Index: 6340071 (Open Web Text)

Max Activating Token Index: 443

Text #9

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9332. Min Act: -0.1697

Data Index: 2271626 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.8383. Min Act: -0.1700

Data Index: 3445860 (Open Web Text)

Max Activating Token Index: 1017

Text #11

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9584. Min Act: -0.1697

Data Index: 809510 (Open Web Text)

Max Activating Token Index: 490

Text #12

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9331. Min Act: -0.1700

Data Index: 3729411 (Open Web Text)

Max Activating Token Index: 761

Text #13

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9774. Min Act: -0.1696

Data Index: 2641440 (Open Web Text)

Max Activating Token Index: 203

Text #14

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9221. Min Act: -0.1643

Data Index: 7932613 (Open Web Text)

Max Activating Token Index: 681

Text #15

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9559. Min Act: -0.1700

Data Index: 1609589 (Open Web Text)

Max Activating Token Index: 1013

Text #16

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9406. Min Act: -0.1699

Data Index: 7038903 (Open Web Text)

Max Activating Token Index: 576

Text #17

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.9649. Min Act: -0.1698

Data Index: 1017458 (Open Web Text)

Max Activating Token Index: 573

Text #18

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.8703. Min Act: -0.1700

Data Index: 5418671 (Open Web Text)

Max Activating Token Index: 972

Text #19

Max Range: 5.2357. Min Range: -5.2357

Max Act: 4.8772. Min Act: -0.1646

Data Index: 1412773 (Open Web Text)

Max Activating Token Index: 303