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

Dataset: Open Web Text

Neuron 1630 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: 7.4444. Min Range: -7.4444

Max Act: 7.4444. Min Act: -0.1700

Data Index: 1385890 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.2750. Min Act: -0.1700

Data Index: 5119392 (Open Web Text)

Max Activating Token Index: 92

Text #2

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.2689. Min Act: -0.1700

Data Index: 6840714 (Open Web Text)

Max Activating Token Index: 724

Text #3

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.2501. Min Act: -0.1700

Data Index: 1405223 (Open Web Text)

Max Activating Token Index: 256

Text #4

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.2082. Min Act: -0.1700

Data Index: 411265 (Open Web Text)

Max Activating Token Index: 722

Text #5

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.1650. Min Act: -0.1700

Data Index: 8746339 (Open Web Text)

Max Activating Token Index: 165

Text #6

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.1471. Min Act: -0.1700

Data Index: 7367486 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.1280. Min Act: -0.1700

Data Index: 3528254 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.0881. Min Act: -0.1700

Data Index: 5742741 (Open Web Text)

Max Activating Token Index: 154

Text #9

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.1026. Min Act: -0.1700

Data Index: 2612083 (Open Web Text)

Max Activating Token Index: 387

Text #10

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.1289. Min Act: -0.1700

Data Index: 4637032 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.0361. Min Act: -0.1700

Data Index: 7716798 (Open Web Text)

Max Activating Token Index: 360

Text #12

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.1024. Min Act: -0.1700

Data Index: 6591684 (Open Web Text)

Max Activating Token Index: 801

Text #13

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.0869. Min Act: -0.1700

Data Index: 7782618 (Open Web Text)

Max Activating Token Index: 921

Text #14

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.0363. Min Act: -0.1700

Data Index: 6662980 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.0558. Min Act: -0.1700

Data Index: 6319402 (Open Web Text)

Max Activating Token Index: 257

Text #16

Max Range: 7.4444. Min Range: -7.4444

Max Act: 7.0212. Min Act: -0.1700

Data Index: 5765499 (Open Web Text)

Max Activating Token Index: 384

Text #17

Max Range: 7.4444. Min Range: -7.4444

Max Act: 6.9335. Min Act: -0.1700

Data Index: 740493 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 7.4444. Min Range: -7.4444

Max Act: 6.9612. Min Act: -0.1700

Data Index: 1899456 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 7.4444. Min Range: -7.4444

Max Act: 6.8770. Min Act: -0.1700

Data Index: 7678403 (Open Web Text)

Max Activating Token Index: 124