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

Dataset: Open Web Text

Neuron 776 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: 3.7160. Min Range: -3.7160

Max Act: 3.7160. Min Act: -0.1700

Data Index: 923779 (Open Web Text)

Max Activating Token Index: 809

Text #1

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.7062. Min Act: -0.1700

Data Index: 5547075 (Open Web Text)

Max Activating Token Index: 358

Text #2

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.6889. Min Act: -0.1700

Data Index: 5042890 (Open Web Text)

Max Activating Token Index: 687

Text #3

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.6548. Min Act: -0.1700

Data Index: 4730240 (Open Web Text)

Max Activating Token Index: 161

Text #4

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.6112. Min Act: -0.1700

Data Index: 7858820 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5798. Min Act: -0.1700

Data Index: 7858821 (Open Web Text)

Max Activating Token Index: 290

Text #6

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5465. Min Act: -0.1700

Data Index: 6023137 (Open Web Text)

Max Activating Token Index: 87

Text #7

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5762. Min Act: -0.1700

Data Index: 6201798 (Open Web Text)

Max Activating Token Index: 228

Text #8

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5833. Min Act: -0.1700

Data Index: 3683777 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5445. Min Act: -0.1700

Data Index: 6318214 (Open Web Text)

Max Activating Token Index: 296

Text #10

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5543. Min Act: -0.1700

Data Index: 2806012 (Open Web Text)

Max Activating Token Index: 637

Text #11

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5425. Min Act: -0.1700

Data Index: 2681400 (Open Web Text)

Max Activating Token Index: 237

Text #12

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5677. Min Act: -0.1700

Data Index: 4730242 (Open Web Text)

Max Activating Token Index: 235

Text #13

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5760. Min Act: -0.1700

Data Index: 213951 (Open Web Text)

Max Activating Token Index: 702

Text #14

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5460. Min Act: -0.1700

Data Index: 2384241 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5227. Min Act: -0.1700

Data Index: 6318212 (Open Web Text)

Max Activating Token Index: 297

Text #16

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5290. Min Act: -0.1700

Data Index: 7368539 (Open Web Text)

Max Activating Token Index: 840

Text #17

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5151. Min Act: -0.1700

Data Index: 3572240 (Open Web Text)

Max Activating Token Index: 745

Text #18

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5406. Min Act: -0.1700

Data Index: 5607135 (Open Web Text)

Max Activating Token Index: 398

Text #19

Max Range: 3.7160. Min Range: -3.7160

Max Act: 3.5258. Min Act: -0.1700

Data Index: 2149984 (Open Web Text)

Max Activating Token Index: 885