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

Dataset: Open Web Text

Neuron 2021 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: 3.8334. Min Range: -3.8334

Max Act: 3.8334. Min Act: -0.1700

Data Index: 6267245 (Open Web Text)

Max Activating Token Index: 191

Text #1

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7631. Min Act: -0.1700

Data Index: 5043009 (Open Web Text)

Max Activating Token Index: 602

Text #2

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7949. Min Act: -0.1700

Data Index: 3303425 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7473. Min Act: -0.1700

Data Index: 6169562 (Open Web Text)

Max Activating Token Index: 388

Text #4

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6796. Min Act: -0.1700

Data Index: 7598693 (Open Web Text)

Max Activating Token Index: 730

Text #5

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7086. Min Act: -0.1700

Data Index: 2991729 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.7169. Min Act: -0.1700

Data Index: 1547759 (Open Web Text)

Max Activating Token Index: 551

Text #7

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6670. Min Act: -0.1700

Data Index: 817097 (Open Web Text)

Max Activating Token Index: 182

Text #8

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6582. Min Act: -0.1700

Data Index: 1497298 (Open Web Text)

Max Activating Token Index: 490

Text #9

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6595. Min Act: -0.1700

Data Index: 359277 (Open Web Text)

Max Activating Token Index: 814

Text #10

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6866. Min Act: -0.1700

Data Index: 8364571 (Open Web Text)

Max Activating Token Index: 217

Text #11

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6920. Min Act: -0.1700

Data Index: 4586285 (Open Web Text)

Max Activating Token Index: 243

Text #12

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6527. Min Act: -0.1700

Data Index: 6490484 (Open Web Text)

Max Activating Token Index: 638

Text #13

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6520. Min Act: -0.1700

Data Index: 8271562 (Open Web Text)

Max Activating Token Index: 346

Text #14

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6306. Min Act: -0.1700

Data Index: 4738021 (Open Web Text)

Max Activating Token Index: 258

Text #15

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6535. Min Act: -0.1700

Data Index: 7299526 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6167. Min Act: -0.1700

Data Index: 1633096 (Open Web Text)

Max Activating Token Index: 510

Text #17

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6478. Min Act: -0.1700

Data Index: 5958103 (Open Web Text)

Max Activating Token Index: 801

Text #18

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6115. Min Act: -0.1700

Data Index: 4696949 (Open Web Text)

Max Activating Token Index: 829

Text #19

Max Range: 3.8334. Min Range: -3.8334

Max Act: 3.6160. Min Act: -0.1700

Data Index: 5568516 (Open Web Text)

Max Activating Token Index: 315