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

Dataset: Open Web Text

Neuron 605 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: 0.4790. Min Range: -0.4790

Max Act: 0.4790. Min Act: -0.1700

Data Index: 270289 (Open Web Text)

Max Activating Token Index: 150

Text #1

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4763. Min Act: -0.1700

Data Index: 6671440 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4586. Min Act: -0.1700

Data Index: 1761200 (Open Web Text)

Max Activating Token Index: 159

Text #3

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4520. Min Act: -0.1686

Data Index: 973029 (Open Web Text)

Max Activating Token Index: 193

Text #4

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4552. Min Act: -0.1647

Data Index: 3958685 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4487. Min Act: -0.1699

Data Index: 2113285 (Open Web Text)

Max Activating Token Index: 113

Text #6

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4448. Min Act: -0.1700

Data Index: 1481758 (Open Web Text)

Max Activating Token Index: 151

Text #7

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4326. Min Act: -0.1692

Data Index: 1859953 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4255. Min Act: -0.1648

Data Index: 2495100 (Open Web Text)

Max Activating Token Index: 841

Text #9

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4331. Min Act: -0.1683

Data Index: 5702945 (Open Web Text)

Max Activating Token Index: 164

Text #10

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4349. Min Act: -0.1698

Data Index: 2722804 (Open Web Text)

Max Activating Token Index: 150

Text #11

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4372. Min Act: -0.1698

Data Index: 8382805 (Open Web Text)

Max Activating Token Index: 209

Text #12

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4277. Min Act: -0.1693

Data Index: 4062170 (Open Web Text)

Max Activating Token Index: 789

Text #13

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4292. Min Act: -0.1699

Data Index: 4635777 (Open Web Text)

Max Activating Token Index: 262

Text #14

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4289. Min Act: -0.1697

Data Index: 3008611 (Open Web Text)

Max Activating Token Index: 94

Text #15

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4241. Min Act: -0.1700

Data Index: 8238020 (Open Web Text)

Max Activating Token Index: 692

Text #16

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4246. Min Act: -0.1699

Data Index: 3269887 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4304. Min Act: -0.1700

Data Index: 6238633 (Open Web Text)

Max Activating Token Index: 706

Text #18

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4253. Min Act: -0.1695

Data Index: 627659 (Open Web Text)

Max Activating Token Index: 291

Text #19

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4290. Min Act: -0.1681

Data Index: 528486 (Open Web Text)

Max Activating Token Index: 6