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

Dataset: Open Web Text

Neuron 1770 in Layer 5

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: 4.9237. Min Range: -4.9237

Max Act: 4.9237. Min Act: -0.1700

Data Index: 5395208 (Open Web Text)

Max Activating Token Index: 940

Text #1

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.8572. Min Act: -0.1700

Data Index: 5371289 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7312. Min Act: -0.1700

Data Index: 7642925 (Open Web Text)

Max Activating Token Index: 556

Text #3

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7621. Min Act: -0.1700

Data Index: 3607758 (Open Web Text)

Max Activating Token Index: 169

Text #4

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7398. Min Act: -0.1700

Data Index: 2077065 (Open Web Text)

Max Activating Token Index: 155

Text #5

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7734. Min Act: -0.1700

Data Index: 3105999 (Open Web Text)

Max Activating Token Index: 242

Text #6

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7189. Min Act: -0.1700

Data Index: 323424 (Open Web Text)

Max Activating Token Index: 759

Text #7

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7576. Min Act: -0.1700

Data Index: 5711375 (Open Web Text)

Max Activating Token Index: 549

Text #8

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7311. Min Act: -0.1700

Data Index: 2064982 (Open Web Text)

Max Activating Token Index: 779

Text #9

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7199. Min Act: -0.1700

Data Index: 7387117 (Open Web Text)

Max Activating Token Index: 959

Text #10

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7096. Min Act: -0.1700

Data Index: 6839506 (Open Web Text)

Max Activating Token Index: 68

Text #11

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7467. Min Act: -0.1700

Data Index: 8060905 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7217. Min Act: -0.1700

Data Index: 5928254 (Open Web Text)

Max Activating Token Index: 446

Text #13

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7221. Min Act: -0.1700

Data Index: 3304438 (Open Web Text)

Max Activating Token Index: 169

Text #14

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.7195. Min Act: -0.1700

Data Index: 3152455 (Open Web Text)

Max Activating Token Index: 270

Text #15

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.6880. Min Act: -0.1700

Data Index: 2266610 (Open Web Text)

Max Activating Token Index: 326

Text #16

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.6324. Min Act: -0.1700

Data Index: 1040527 (Open Web Text)

Max Activating Token Index: 586

Text #17

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.6758. Min Act: -0.1700

Data Index: 3942413 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.6880. Min Act: -0.1700

Data Index: 4117639 (Open Web Text)

Max Activating Token Index: 908

Text #19

Max Range: 4.9237. Min Range: -4.9237

Max Act: 4.6931. Min Act: -0.1700

Data Index: 7767073 (Open Web Text)

Max Activating Token Index: 578