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

Dataset: Open Web Text

Neuron 1269 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: 0.8604. Min Range: -0.8604

Max Act: 0.8533. Min Act: -0.1700

Data Index: 2555452 (Open Web Text)

Max Activating Token Index: 488

Text #1

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8502. Min Act: -0.1700

Data Index: 8538675 (Open Web Text)

Max Activating Token Index: 212

Text #2

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8537. Min Act: -0.1700

Data Index: 8721607 (Open Web Text)

Max Activating Token Index: 587

Text #3

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8604. Min Act: -0.1700

Data Index: 4672603 (Open Web Text)

Max Activating Token Index: 477

Text #4

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8399. Min Act: -0.1700

Data Index: 4756313 (Open Web Text)

Max Activating Token Index: 301

Text #5

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8253. Min Act: -0.1700

Data Index: 2733460 (Open Web Text)

Max Activating Token Index: 392

Text #6

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8163. Min Act: -0.1700

Data Index: 2449080 (Open Web Text)

Max Activating Token Index: 451

Text #7

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8176. Min Act: -0.1700

Data Index: 1361530 (Open Web Text)

Max Activating Token Index: 335

Text #8

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7871. Min Act: -0.1700

Data Index: 1150071 (Open Web Text)

Max Activating Token Index: 282

Text #9

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7768. Min Act: -0.1700

Data Index: 4021940 (Open Web Text)

Max Activating Token Index: 826

Text #10

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7784. Min Act: -0.1700

Data Index: 2077434 (Open Web Text)

Max Activating Token Index: 655

Text #11

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7864. Min Act: -0.1700

Data Index: 1862165 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7737. Min Act: -0.1700

Data Index: 5923345 (Open Web Text)

Max Activating Token Index: 376

Text #13

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7672. Min Act: -0.1700

Data Index: 8538654 (Open Web Text)

Max Activating Token Index: 231

Text #14

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7510. Min Act: -0.1700

Data Index: 1543782 (Open Web Text)

Max Activating Token Index: 646

Text #15

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7525. Min Act: -0.1700

Data Index: 3760238 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7476. Min Act: -0.1700

Data Index: 8782212 (Open Web Text)

Max Activating Token Index: 516

Text #17

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7434. Min Act: -0.1700

Data Index: 8538661 (Open Web Text)

Max Activating Token Index: 440

Text #18

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7285. Min Act: -0.1700

Data Index: 2413696 (Open Web Text)

Max Activating Token Index: 497

Text #19

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7300. Min Act: -0.1700

Data Index: 4983923 (Open Web Text)

Max Activating Token Index: 842