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

Dataset: Open Web Text

Neuron 455 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: 2.7147. Min Range: -2.7147

Max Act: 2.7147. Min Act: -0.1699

Data Index: 1317588 (Open Web Text)

Max Activating Token Index: 178

Text #1

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.5493. Min Act: -0.1661

Data Index: 1991957 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.5349. Min Act: -0.1700

Data Index: 4310810 (Open Web Text)

Max Activating Token Index: 357

Text #3

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.5023. Min Act: -0.1700

Data Index: 6719998 (Open Web Text)

Max Activating Token Index: 269

Text #4

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.4868. Min Act: -0.1700

Data Index: 75911 (Open Web Text)

Max Activating Token Index: 457

Text #5

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.4034. Min Act: -0.1686

Data Index: 7634611 (Open Web Text)

Max Activating Token Index: 487

Text #6

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.3822. Min Act: -0.1700

Data Index: 1642780 (Open Web Text)

Max Activating Token Index: 351

Text #7

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.3535. Min Act: -0.1700

Data Index: 1585884 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.3563. Min Act: -0.1700

Data Index: 8563862 (Open Web Text)

Max Activating Token Index: 958

Text #9

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.3422. Min Act: -0.1700

Data Index: 8651914 (Open Web Text)

Max Activating Token Index: 264

Text #10

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.3438. Min Act: -0.1700

Data Index: 7181651 (Open Web Text)

Max Activating Token Index: 482

Text #11

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.3398. Min Act: -0.1700

Data Index: 2509718 (Open Web Text)

Max Activating Token Index: 371

Text #12

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.3033. Min Act: -0.1700

Data Index: 2792863 (Open Web Text)

Max Activating Token Index: 378

Text #13

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.2622. Min Act: -0.1693

Data Index: 6721280 (Open Web Text)

Max Activating Token Index: 254

Text #14

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.2769. Min Act: -0.1700

Data Index: 5716682 (Open Web Text)

Max Activating Token Index: 552

Text #15

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.2193. Min Act: -0.1695

Data Index: 1373839 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.1849. Min Act: -0.1700

Data Index: 8685970 (Open Web Text)

Max Activating Token Index: 838

Text #17

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.2277. Min Act: -0.1700

Data Index: 444047 (Open Web Text)

Max Activating Token Index: 362

Text #18

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.2255. Min Act: -0.1700

Data Index: 3995853 (Open Web Text)

Max Activating Token Index: 363

Text #19

Max Range: 2.7147. Min Range: -2.7147

Max Act: 2.1726. Min Act: -0.1700

Data Index: 4189525 (Open Web Text)

Max Activating Token Index: 446