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

Dataset: Open Web Text

Neuron 1501 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: 4.3507. Min Range: -4.3507

Max Act: 4.3507. Min Act: -0.1700

Data Index: 3687647 (Open Web Text)

Max Activating Token Index: 432

Text #1

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.3379. Min Act: -0.1700

Data Index: 8476404 (Open Web Text)

Max Activating Token Index: 673

Text #2

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.3115. Min Act: -0.1700

Data Index: 6018191 (Open Web Text)

Max Activating Token Index: 178

Text #3

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.2617. Min Act: -0.1700

Data Index: 1434379 (Open Web Text)

Max Activating Token Index: 375

Text #4

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.2197. Min Act: -0.1700

Data Index: 765476 (Open Web Text)

Max Activating Token Index: 321

Text #5

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.2434. Min Act: -0.1700

Data Index: 1338742 (Open Web Text)

Max Activating Token Index: 692

Text #6

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.2751. Min Act: -0.1700

Data Index: 899179 (Open Web Text)

Max Activating Token Index: 590

Text #7

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.2736. Min Act: -0.1700

Data Index: 6116172 (Open Web Text)

Max Activating Token Index: 156

Text #8

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.3017. Min Act: -0.1700

Data Index: 8057818 (Open Web Text)

Max Activating Token Index: 481

Text #9

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.2145. Min Act: -0.1700

Data Index: 6179504 (Open Web Text)

Max Activating Token Index: 94

Text #10

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.2291. Min Act: -0.1700

Data Index: 6379920 (Open Web Text)

Max Activating Token Index: 230

Text #11

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.1892. Min Act: -0.1700

Data Index: 8053628 (Open Web Text)

Max Activating Token Index: 79

Text #12

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.1334. Min Act: -0.1700

Data Index: 3439008 (Open Web Text)

Max Activating Token Index: 301

Text #13

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.1799. Min Act: -0.1700

Data Index: 3585454 (Open Web Text)

Max Activating Token Index: 207

Text #14

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.1334. Min Act: -0.1700

Data Index: 6543542 (Open Web Text)

Max Activating Token Index: 457

Text #15

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.1074. Min Act: -0.1700

Data Index: 3011517 (Open Web Text)

Max Activating Token Index: 700

Text #16

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.1282. Min Act: -0.1700

Data Index: 5833325 (Open Web Text)

Max Activating Token Index: 150

Text #17

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.1016. Min Act: -0.1700

Data Index: 8760942 (Open Web Text)

Max Activating Token Index: 469

Text #18

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.1256. Min Act: -0.1700

Data Index: 6981013 (Open Web Text)

Max Activating Token Index: 482

Text #19

Max Range: 4.3507. Min Range: -4.3507

Max Act: 4.0733. Min Act: -0.1700

Data Index: 1883465 (Open Web Text)

Max Activating Token Index: 586