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

Dataset: Open Web Text

Neuron 472 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: 1.8722. Min Range: -1.8722

Max Act: 1.8722. Min Act: -0.1700

Data Index: 2451604 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8678. Min Act: -0.1700

Data Index: 7638573 (Open Web Text)

Max Activating Token Index: 427

Text #2

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8493. Min Act: -0.1700

Data Index: 6810584 (Open Web Text)

Max Activating Token Index: 398

Text #3

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8586. Min Act: -0.1700

Data Index: 8585854 (Open Web Text)

Max Activating Token Index: 240

Text #4

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8475. Min Act: -0.1700

Data Index: 1673517 (Open Web Text)

Max Activating Token Index: 221

Text #5

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8483. Min Act: -0.1700

Data Index: 4250012 (Open Web Text)

Max Activating Token Index: 505

Text #6

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8475. Min Act: -0.1700

Data Index: 2751090 (Open Web Text)

Max Activating Token Index: 290

Text #7

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8454. Min Act: -0.1700

Data Index: 48588 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8253. Min Act: -0.1700

Data Index: 1762655 (Open Web Text)

Max Activating Token Index: 434

Text #9

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8374. Min Act: -0.1700

Data Index: 3521389 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8321. Min Act: -0.1700

Data Index: 5054952 (Open Web Text)

Max Activating Token Index: 236

Text #11

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8306. Min Act: -0.1700

Data Index: 8396139 (Open Web Text)

Max Activating Token Index: 223

Text #12

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8267. Min Act: -0.1700

Data Index: 1250167 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8170. Min Act: -0.1700

Data Index: 2046062 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8125. Min Act: -0.1693

Data Index: 1384066 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8145. Min Act: -0.1700

Data Index: 6799635 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8187. Min Act: -0.1699

Data Index: 8063941 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8192. Min Act: -0.1695

Data Index: 3709109 (Open Web Text)

Max Activating Token Index: 433

Text #18

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8080. Min Act: -0.1700

Data Index: 6322198 (Open Web Text)

Max Activating Token Index: 1002

Text #19

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8236. Min Act: -0.1699

Data Index: 1826342 (Open Web Text)

Max Activating Token Index: 259