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

Dataset: Open Web Text

Neuron 2974 in Layer 0

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: 1.5682. Min Range: -1.5682

Max Act: 1.5682. Min Act: -0.1700

Data Index: 1798638 (Open Web Text)

Max Activating Token Index: 293

Text #1

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5466. Min Act: -0.1700

Data Index: 3060426 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5443. Min Act: -0.1700

Data Index: 1717362 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5440. Min Act: -0.1700

Data Index: 2942151 (Open Web Text)

Max Activating Token Index: 490

Text #4

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5547. Min Act: -0.1700

Data Index: 4681669 (Open Web Text)

Max Activating Token Index: 236

Text #5

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5389. Min Act: -0.1700

Data Index: 2780848 (Open Web Text)

Max Activating Token Index: 592

Text #6

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5367. Min Act: -0.1700

Data Index: 1636293 (Open Web Text)

Max Activating Token Index: 402

Text #7

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5481. Min Act: -0.1700

Data Index: 4016795 (Open Web Text)

Max Activating Token Index: 578

Text #8

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5176. Min Act: -0.1699

Data Index: 3848190 (Open Web Text)

Max Activating Token Index: 449

Text #9

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5271. Min Act: -0.1700

Data Index: 1055975 (Open Web Text)

Max Activating Token Index: 40

Text #10

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5318. Min Act: -0.1692

Data Index: 4364929 (Open Web Text)

Max Activating Token Index: 562

Text #11

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5361. Min Act: -0.1700

Data Index: 3691546 (Open Web Text)

Max Activating Token Index: 235

Text #12

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5320. Min Act: -0.1579

Data Index: 7062443 (Open Web Text)

Max Activating Token Index: 599

Text #13

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5324. Min Act: -0.1695

Data Index: 1866347 (Open Web Text)

Max Activating Token Index: 266

Text #14

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5340. Min Act: -0.1700

Data Index: 586155 (Open Web Text)

Max Activating Token Index: 679

Text #15

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5284. Min Act: -0.1700

Data Index: 4511393 (Open Web Text)

Max Activating Token Index: 230

Text #16

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5384. Min Act: -0.1700

Data Index: 2376210 (Open Web Text)

Max Activating Token Index: 748

Text #17

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5254. Min Act: -0.1700

Data Index: 1760665 (Open Web Text)

Max Activating Token Index: 434

Text #18

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5281. Min Act: -0.1616

Data Index: 4165380 (Open Web Text)

Max Activating Token Index: 623

Text #19

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5168. Min Act: -0.1691

Data Index: 2016682 (Open Web Text)

Max Activating Token Index: 477