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

Dataset: Open Web Text

Neuron 2254 in Layer 0

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: 1.4916. Min Range: -1.4916

Max Act: 1.4916. Min Act: -0.1430

Data Index: 1234461 (Open Web Text)

Max Activating Token Index: 384

Text #1

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4773. Min Act: -0.1292

Data Index: 4967608 (Open Web Text)

Max Activating Token Index: 590

Text #2

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4876. Min Act: -0.1523

Data Index: 6042768 (Open Web Text)

Max Activating Token Index: 711

Text #3

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4784. Min Act: -0.1532

Data Index: 1892484 (Open Web Text)

Max Activating Token Index: 629

Text #4

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4736. Min Act: -0.1387

Data Index: 5089962 (Open Web Text)

Max Activating Token Index: 375

Text #5

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4650. Min Act: -0.1661

Data Index: 8528944 (Open Web Text)

Max Activating Token Index: 358

Text #6

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4605. Min Act: -0.1490

Data Index: 4217827 (Open Web Text)

Max Activating Token Index: 661

Text #7

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4606. Min Act: -0.1667

Data Index: 2243272 (Open Web Text)

Max Activating Token Index: 676

Text #8

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4538. Min Act: -0.1698

Data Index: 5194136 (Open Web Text)

Max Activating Token Index: 463

Text #9

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4528. Min Act: -0.1550

Data Index: 2455481 (Open Web Text)

Max Activating Token Index: 594

Text #10

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4528. Min Act: -0.1676

Data Index: 5920266 (Open Web Text)

Max Activating Token Index: 418

Text #11

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4526. Min Act: -0.1246

Data Index: 5788449 (Open Web Text)

Max Activating Token Index: 464

Text #12

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4476. Min Act: -0.1653

Data Index: 441365 (Open Web Text)

Max Activating Token Index: 125

Text #13

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4426. Min Act: -0.1135

Data Index: 7438071 (Open Web Text)

Max Activating Token Index: 608

Text #14

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4438. Min Act: -0.1696

Data Index: 1778092 (Open Web Text)

Max Activating Token Index: 217

Text #15

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4362. Min Act: -0.1370

Data Index: 6009306 (Open Web Text)

Max Activating Token Index: 397

Text #16

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4356. Min Act: -0.1594

Data Index: 5120209 (Open Web Text)

Max Activating Token Index: 370

Text #17

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4332. Min Act: -0.1676

Data Index: 4823994 (Open Web Text)

Max Activating Token Index: 548

Text #18

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4371. Min Act: -0.1590

Data Index: 2799326 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.4354. Min Act: -0.1698

Data Index: 6740759 (Open Web Text)

Max Activating Token Index: 249