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

Dataset: Open Web Text

Neuron 2321 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: 3.7252. Min Range: -3.7252

Max Act: 3.7252. Min Act: -0.1700

Data Index: 6329157 (Open Web Text)

Max Activating Token Index: 716

Text #1

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.6487. Min Act: -0.1700

Data Index: 2360660 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.6038. Min Act: -0.1700

Data Index: 1654825 (Open Web Text)

Max Activating Token Index: 210

Text #3

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.5545. Min Act: -0.1700

Data Index: 1298528 (Open Web Text)

Max Activating Token Index: 865

Text #4

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.5394. Min Act: -0.1700

Data Index: 7395534 (Open Web Text)

Max Activating Token Index: 517

Text #5

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.5293. Min Act: -0.1700

Data Index: 7046389 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4964. Min Act: -0.1700

Data Index: 3909035 (Open Web Text)

Max Activating Token Index: 384

Text #7

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4702. Min Act: -0.1700

Data Index: 7129460 (Open Web Text)

Max Activating Token Index: 366

Text #8

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4872. Min Act: -0.1700

Data Index: 7455804 (Open Web Text)

Max Activating Token Index: 511

Text #9

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4930. Min Act: -0.1700

Data Index: 8661723 (Open Web Text)

Max Activating Token Index: 490

Text #10

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4895. Min Act: -0.1700

Data Index: 484389 (Open Web Text)

Max Activating Token Index: 339

Text #11

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4565. Min Act: -0.1700

Data Index: 5640552 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4749. Min Act: -0.1700

Data Index: 4578033 (Open Web Text)

Max Activating Token Index: 328

Text #13

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4535. Min Act: -0.1700

Data Index: 8744266 (Open Web Text)

Max Activating Token Index: 516

Text #14

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4431. Min Act: -0.1700

Data Index: 8439675 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4435. Min Act: -0.1700

Data Index: 1751569 (Open Web Text)

Max Activating Token Index: 448

Text #16

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4553. Min Act: -0.1700

Data Index: 1744756 (Open Web Text)

Max Activating Token Index: 469

Text #17

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4292. Min Act: -0.1700

Data Index: 4088596 (Open Web Text)

Max Activating Token Index: 327

Text #18

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4096. Min Act: -0.1700

Data Index: 2319639 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 3.7252. Min Range: -3.7252

Max Act: 3.4237. Min Act: -0.1700

Data Index: 759262 (Open Web Text)

Max Activating Token Index: 392