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

Dataset: Open Web Text

Neuron 2536 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: 1.3116. Min Range: -1.3116

Max Act: 1.3116. Min Act: -0.1700

Data Index: 6326315 (Open Web Text)

Max Activating Token Index: 570

Text #1

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2735. Min Act: -0.1696

Data Index: 542400 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2671. Min Act: -0.1570

Data Index: 8248593 (Open Web Text)

Max Activating Token Index: 630

Text #3

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2638. Min Act: -0.1697

Data Index: 3231592 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2577. Min Act: -0.1679

Data Index: 8248596 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2461. Min Act: -0.1693

Data Index: 2828100 (Open Web Text)

Max Activating Token Index: 533

Text #6

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2518. Min Act: -0.1700

Data Index: 4162201 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2379. Min Act: -0.1572

Data Index: 2063351 (Open Web Text)

Max Activating Token Index: 836

Text #8

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2536. Min Act: -0.1699

Data Index: 2435928 (Open Web Text)

Max Activating Token Index: 771

Text #9

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2536. Min Act: -0.1577

Data Index: 8248595 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2436. Min Act: -0.1682

Data Index: 7913737 (Open Web Text)

Max Activating Token Index: 891

Text #11

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2479. Min Act: -0.1699

Data Index: 8453683 (Open Web Text)

Max Activating Token Index: 266

Text #12

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2373. Min Act: -0.1587

Data Index: 7923248 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2444. Min Act: -0.1700

Data Index: 1536898 (Open Web Text)

Max Activating Token Index: 527

Text #14

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2471. Min Act: -0.1681

Data Index: 8493186 (Open Web Text)

Max Activating Token Index: 620

Text #15

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2506. Min Act: -0.1480

Data Index: 7252064 (Open Web Text)

Max Activating Token Index: 531

Text #16

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2456. Min Act: -0.1545

Data Index: 7950440 (Open Web Text)

Max Activating Token Index: 854

Text #17

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2493. Min Act: -0.1599

Data Index: 2599523 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2354. Min Act: -0.1645

Data Index: 5750211 (Open Web Text)

Max Activating Token Index: 230

Text #19

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.2346. Min Act: -0.1671

Data Index: 8033718 (Open Web Text)

Max Activating Token Index: 488