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

Dataset: Open Web Text

Neuron 892 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: 1.8747. Min Range: -1.8747

Max Act: 1.8747. Min Act: 0.0520

Data Index: 8286663 (Open Web Text)

Max Activating Token Index: 526

Text #1

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8659. Min Act: 0.0744

Data Index: 765867 (Open Web Text)

Max Activating Token Index: 604

Text #2

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8603. Min Act: 0.0583

Data Index: 823556 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8558. Min Act: 0.0547

Data Index: 2889735 (Open Web Text)

Max Activating Token Index: 561

Text #4

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8557. Min Act: 0.1003

Data Index: 1109742 (Open Web Text)

Max Activating Token Index: 612

Text #5

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8467. Min Act: 0.0601

Data Index: 7524290 (Open Web Text)

Max Activating Token Index: 297

Text #6

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8480. Min Act: 0.0602

Data Index: 810273 (Open Web Text)

Max Activating Token Index: 601

Text #7

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8543. Min Act: 0.1588

Data Index: 2716903 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8522. Min Act: -0.0695

Data Index: 4737122 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8482. Min Act: 0.1167

Data Index: 365821 (Open Web Text)

Max Activating Token Index: 529

Text #10

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8449. Min Act: 0.0407

Data Index: 2224046 (Open Web Text)

Max Activating Token Index: 338

Text #11

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8465. Min Act: 0.0002

Data Index: 2087936 (Open Web Text)

Max Activating Token Index: 347

Text #12

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8428. Min Act: 0.0600

Data Index: 8472341 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8378. Min Act: 0.0395

Data Index: 4928930 (Open Web Text)

Max Activating Token Index: 585

Text #14

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8412. Min Act: 0.0657

Data Index: 5008993 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8405. Min Act: 0.0415

Data Index: 7260082 (Open Web Text)

Max Activating Token Index: 355

Text #16

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8342. Min Act: 0.0081

Data Index: 3593411 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8334. Min Act: 0.0347

Data Index: 2545296 (Open Web Text)

Max Activating Token Index: 294

Text #18

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8364. Min Act: -0.0001

Data Index: 1538362 (Open Web Text)

Max Activating Token Index: 564

Text #19

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8330. Min Act: 0.0225

Data Index: 2908209 (Open Web Text)

Max Activating Token Index: 382