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

Dataset: Open Web Text

Neuron 2806 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: 5.4827. Min Range: -5.4827

Max Act: 5.4827. Min Act: -0.1700

Data Index: 1445173 (Open Web Text)

Max Activating Token Index: 414

Text #1

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.4692. Min Act: -0.1700

Data Index: 1760785 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.3649. Min Act: -0.1700

Data Index: 6387281 (Open Web Text)

Max Activating Token Index: 677

Text #3

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.3572. Min Act: -0.1700

Data Index: 5310517 (Open Web Text)

Max Activating Token Index: 160

Text #4

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.3775. Min Act: -0.1700

Data Index: 6165146 (Open Web Text)

Max Activating Token Index: 375

Text #5

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.3331. Min Act: -0.1700

Data Index: 7248087 (Open Web Text)

Max Activating Token Index: 731

Text #6

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.3014. Min Act: -0.1700

Data Index: 6177612 (Open Web Text)

Max Activating Token Index: 310

Text #7

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2893. Min Act: -0.1700

Data Index: 763350 (Open Web Text)

Max Activating Token Index: 485

Text #8

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2442. Min Act: -0.1700

Data Index: 6180877 (Open Web Text)

Max Activating Token Index: 618

Text #9

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2747. Min Act: -0.1700

Data Index: 5050320 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2601. Min Act: -0.1700

Data Index: 2591440 (Open Web Text)

Max Activating Token Index: 925

Text #11

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2400. Min Act: -0.1700

Data Index: 4582185 (Open Web Text)

Max Activating Token Index: 867

Text #12

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2361. Min Act: -0.1700

Data Index: 4916735 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2601. Min Act: -0.1700

Data Index: 1562532 (Open Web Text)

Max Activating Token Index: 878

Text #14

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2533. Min Act: -0.1700

Data Index: 5011005 (Open Web Text)

Max Activating Token Index: 319

Text #15

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2130. Min Act: -0.1700

Data Index: 8014492 (Open Web Text)

Max Activating Token Index: 170

Text #16

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2335. Min Act: -0.1700

Data Index: 846883 (Open Web Text)

Max Activating Token Index: 689

Text #17

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2358. Min Act: -0.1700

Data Index: 3633597 (Open Web Text)

Max Activating Token Index: 579

Text #18

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.1956. Min Act: -0.1700

Data Index: 4239293 (Open Web Text)

Max Activating Token Index: 409

Text #19

Max Range: 5.4827. Min Range: -5.4827

Max Act: 5.2032. Min Act: -0.1700

Data Index: 4338766 (Open Web Text)

Max Activating Token Index: 488