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

Dataset: Open Web Text

Neuron 293 in Layer 1

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: 1.5937. Min Range: -1.5937

Max Act: 1.5937. Min Act: -0.1150

Data Index: 3762431 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5649. Min Act: -0.1682

Data Index: 1986956 (Open Web Text)

Max Activating Token Index: 414

Text #2

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5429. Min Act: -0.1532

Data Index: 719948 (Open Web Text)

Max Activating Token Index: 133

Text #3

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5476. Min Act: -0.1639

Data Index: 2994478 (Open Web Text)

Max Activating Token Index: 230

Text #4

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5408. Min Act: -0.1551

Data Index: 255048 (Open Web Text)

Max Activating Token Index: 759

Text #5

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5326. Min Act: -0.1434

Data Index: 3183042 (Open Web Text)

Max Activating Token Index: 284

Text #6

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5433. Min Act: -0.1435

Data Index: 1638352 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5313. Min Act: -0.1459

Data Index: 7238345 (Open Web Text)

Max Activating Token Index: 270

Text #8

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5290. Min Act: -0.1130

Data Index: 3762428 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5229. Min Act: -0.1452

Data Index: 719949 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5136. Min Act: -0.1691

Data Index: 4132547 (Open Web Text)

Max Activating Token Index: 456

Text #11

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5062. Min Act: -0.1569

Data Index: 3662938 (Open Web Text)

Max Activating Token Index: 409

Text #12

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5159. Min Act: -0.1410

Data Index: 1287475 (Open Web Text)

Max Activating Token Index: 374

Text #13

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5050. Min Act: -0.1637

Data Index: 4132542 (Open Web Text)

Max Activating Token Index: 340

Text #14

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4848. Min Act: -0.1480

Data Index: 6400799 (Open Web Text)

Max Activating Token Index: 124

Text #15

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4919. Min Act: -0.1310

Data Index: 1986949 (Open Web Text)

Max Activating Token Index: 70

Text #16

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4918. Min Act: -0.1561

Data Index: 5659936 (Open Web Text)

Max Activating Token Index: 446

Text #17

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4818. Min Act: -0.1655

Data Index: 4683771 (Open Web Text)

Max Activating Token Index: 155

Text #18

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4775. Min Act: -0.1421

Data Index: 2890933 (Open Web Text)

Max Activating Token Index: 354

Text #19

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4728. Min Act: -0.1472

Data Index: 3099309 (Open Web Text)

Max Activating Token Index: 103