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

Dataset: Open Web Text

Neuron 2227 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: 4.4465. Min Range: -4.4465

Max Act: 4.4465. Min Act: -0.1700

Data Index: 6297171 (Open Web Text)

Max Activating Token Index: 947

Text #1

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.3709. Min Act: -0.1700

Data Index: 3349383 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.3234. Min Act: -0.1700

Data Index: 3859042 (Open Web Text)

Max Activating Token Index: 670

Text #3

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.3384. Min Act: -0.1700

Data Index: 4631243 (Open Web Text)

Max Activating Token Index: 682

Text #4

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.2737. Min Act: -0.1700

Data Index: 2935676 (Open Web Text)

Max Activating Token Index: 547

Text #5

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.2258. Min Act: -0.1700

Data Index: 7673571 (Open Web Text)

Max Activating Token Index: 559

Text #6

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.2236. Min Act: -0.1700

Data Index: 6353466 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.2093. Min Act: -0.1700

Data Index: 3333424 (Open Web Text)

Max Activating Token Index: 260

Text #8

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.2052. Min Act: -0.1700

Data Index: 1386691 (Open Web Text)

Max Activating Token Index: 948

Text #9

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1676. Min Act: -0.1700

Data Index: 6994476 (Open Web Text)

Max Activating Token Index: 82

Text #10

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1699. Min Act: -0.1700

Data Index: 7428548 (Open Web Text)

Max Activating Token Index: 113

Text #11

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1658. Min Act: -0.1700

Data Index: 8185726 (Open Web Text)

Max Activating Token Index: 277

Text #12

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1617. Min Act: -0.1700

Data Index: 1242131 (Open Web Text)

Max Activating Token Index: 499

Text #13

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1485. Min Act: -0.1700

Data Index: 571366 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1544. Min Act: -0.1700

Data Index: 4739740 (Open Web Text)

Max Activating Token Index: 232

Text #15

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1784. Min Act: -0.1700

Data Index: 5418521 (Open Web Text)

Max Activating Token Index: 787

Text #16

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1618. Min Act: -0.1700

Data Index: 1514010 (Open Web Text)

Max Activating Token Index: 265

Text #17

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1373. Min Act: -0.1700

Data Index: 224721 (Open Web Text)

Max Activating Token Index: 310

Text #18

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1385. Min Act: -0.1700

Data Index: 2386443 (Open Web Text)

Max Activating Token Index: 974

Text #19

Max Range: 4.4465. Min Range: -4.4465

Max Act: 4.1341. Min Act: -0.1700

Data Index: 5764499 (Open Web Text)

Max Activating Token Index: 447