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

Dataset: Open Web Text

Neuron 1343 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: 6.3412. Min Range: -6.3412

Max Act: 6.3412. Min Act: -0.1700

Data Index: 6087760 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2803. Min Act: -0.1700

Data Index: 2703294 (Open Web Text)

Max Activating Token Index: 580

Text #2

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2962. Min Act: -0.1700

Data Index: 5845865 (Open Web Text)

Max Activating Token Index: 555

Text #3

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2717. Min Act: -0.1700

Data Index: 6578827 (Open Web Text)

Max Activating Token Index: 347

Text #4

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2404. Min Act: -0.1700

Data Index: 8077746 (Open Web Text)

Max Activating Token Index: 317

Text #5

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2624. Min Act: -0.1700

Data Index: 3106072 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2640. Min Act: -0.1700

Data Index: 534278 (Open Web Text)

Max Activating Token Index: 202

Text #7

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2735. Min Act: -0.1700

Data Index: 982922 (Open Web Text)

Max Activating Token Index: 488

Text #8

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2682. Min Act: -0.1700

Data Index: 637336 (Open Web Text)

Max Activating Token Index: 547

Text #9

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2503. Min Act: -0.1700

Data Index: 4277133 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2304. Min Act: -0.1700

Data Index: 8041953 (Open Web Text)

Max Activating Token Index: 616

Text #11

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2224. Min Act: -0.1700

Data Index: 6839906 (Open Web Text)

Max Activating Token Index: 380

Text #12

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2398. Min Act: -0.1700

Data Index: 3654799 (Open Web Text)

Max Activating Token Index: 372

Text #13

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2562. Min Act: -0.1700

Data Index: 3612483 (Open Web Text)

Max Activating Token Index: 211

Text #14

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2189. Min Act: -0.1700

Data Index: 6428245 (Open Web Text)

Max Activating Token Index: 393

Text #15

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2217. Min Act: -0.1700

Data Index: 6026135 (Open Web Text)

Max Activating Token Index: 449

Text #16

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2262. Min Act: -0.1700

Data Index: 2304251 (Open Web Text)

Max Activating Token Index: 522

Text #17

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2310. Min Act: -0.1700

Data Index: 5174513 (Open Web Text)

Max Activating Token Index: 671

Text #18

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2446. Min Act: -0.1700

Data Index: 3177139 (Open Web Text)

Max Activating Token Index: 387

Text #19

Max Range: 6.3412. Min Range: -6.3412

Max Act: 6.2397. Min Act: -0.1700

Data Index: 4500908 (Open Web Text)

Max Activating Token Index: 463