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

Dataset: Open Web Text

Neuron 1322 in Layer 4

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: 2.3515. Min Range: -2.3515

Max Act: 2.3515. Min Act: -0.1305

Data Index: 4310353 (Open Web Text)

Max Activating Token Index: 497

Text #1

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2565. Min Act: -0.1407

Data Index: 5698766 (Open Web Text)

Max Activating Token Index: 373

Text #2

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2545. Min Act: -0.1470

Data Index: 5035087 (Open Web Text)

Max Activating Token Index: 460

Text #3

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2625. Min Act: -0.1481

Data Index: 2080508 (Open Web Text)

Max Activating Token Index: 537

Text #4

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2587. Min Act: -0.1305

Data Index: 4170968 (Open Web Text)

Max Activating Token Index: 411

Text #5

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2639. Min Act: -0.1659

Data Index: 8052927 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2595. Min Act: -0.1697

Data Index: 3782002 (Open Web Text)

Max Activating Token Index: 542

Text #7

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2465. Min Act: -0.1305

Data Index: 6189555 (Open Web Text)

Max Activating Token Index: 674

Text #8

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2374. Min Act: -0.1305

Data Index: 4613845 (Open Web Text)

Max Activating Token Index: 700

Text #9

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2429. Min Act: -0.1305

Data Index: 6991652 (Open Web Text)

Max Activating Token Index: 541

Text #10

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2466. Min Act: -0.1444

Data Index: 1586436 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2156. Min Act: -0.1305

Data Index: 1126543 (Open Web Text)

Max Activating Token Index: 338

Text #12

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2090. Min Act: -0.1466

Data Index: 7564449 (Open Web Text)

Max Activating Token Index: 898

Text #13

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2199. Min Act: -0.1378

Data Index: 4494048 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2139. Min Act: -0.1305

Data Index: 1153096 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2036. Min Act: -0.1451

Data Index: 4458215 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.2115. Min Act: -0.1305

Data Index: 2081513 (Open Web Text)

Max Activating Token Index: 447

Text #17

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.1719. Min Act: -0.1305

Data Index: 8643857 (Open Web Text)

Max Activating Token Index: 516

Text #18

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.1699. Min Act: -0.1308

Data Index: 2833729 (Open Web Text)

Max Activating Token Index: 527

Text #19

Max Range: 2.3515. Min Range: -2.3515

Max Act: 2.1824. Min Act: -0.1305

Data Index: 4208633 (Open Web Text)

Max Activating Token Index: 494