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

Dataset: Open Web Text

Neuron 2348 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: 4.4190. Min Range: -4.4190

Max Act: 4.4190. Min Act: -0.1700

Data Index: 446635 (Open Web Text)

Max Activating Token Index: 966

Text #1

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.3724. Min Act: -0.1700

Data Index: 6007586 (Open Web Text)

Max Activating Token Index: 335

Text #2

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.3479. Min Act: -0.1700

Data Index: 6582003 (Open Web Text)

Max Activating Token Index: 411

Text #3

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.3115. Min Act: -0.1700

Data Index: 4997835 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.3124. Min Act: -0.1700

Data Index: 6855607 (Open Web Text)

Max Activating Token Index: 321

Text #5

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2930. Min Act: -0.1700

Data Index: 6026224 (Open Web Text)

Max Activating Token Index: 354

Text #6

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2196. Min Act: -0.1700

Data Index: 2262459 (Open Web Text)

Max Activating Token Index: 59

Text #7

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2548. Min Act: -0.1700

Data Index: 6458486 (Open Web Text)

Max Activating Token Index: 571

Text #8

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2618. Min Act: -0.1700

Data Index: 7804680 (Open Web Text)

Max Activating Token Index: 486

Text #9

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2771. Min Act: -0.1700

Data Index: 4549169 (Open Web Text)

Max Activating Token Index: 432

Text #10

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2622. Min Act: -0.1700

Data Index: 4611471 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2272. Min Act: -0.1700

Data Index: 5369512 (Open Web Text)

Max Activating Token Index: 399

Text #12

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2452. Min Act: -0.1700

Data Index: 7021388 (Open Web Text)

Max Activating Token Index: 577

Text #13

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2529. Min Act: -0.1700

Data Index: 99756 (Open Web Text)

Max Activating Token Index: 961

Text #14

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2623. Min Act: -0.1700

Data Index: 7673901 (Open Web Text)

Max Activating Token Index: 151

Text #15

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2284. Min Act: -0.1700

Data Index: 553481 (Open Web Text)

Max Activating Token Index: 532

Text #16

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2194. Min Act: -0.1700

Data Index: 2575249 (Open Web Text)

Max Activating Token Index: 495

Text #17

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2240. Min Act: -0.1700

Data Index: 3309676 (Open Web Text)

Max Activating Token Index: 428

Text #18

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2525. Min Act: -0.1700

Data Index: 4796303 (Open Web Text)

Max Activating Token Index: 563

Text #19

Max Range: 4.4190. Min Range: -4.4190

Max Act: 4.2430. Min Act: -0.1700

Data Index: 3438469 (Open Web Text)

Max Activating Token Index: 468