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

Dataset: Open Web Text

Neuron 1199 in Layer 5

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: 5.2183. Min Range: -5.2183

Max Act: 5.1797. Min Act: -0.1700

Data Index: 2315068 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1931. Min Act: -0.1700

Data Index: 4725992 (Open Web Text)

Max Activating Token Index: 52

Text #2

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1988. Min Act: -0.1700

Data Index: 1459258 (Open Web Text)

Max Activating Token Index: 300

Text #3

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.2183. Min Act: -0.1700

Data Index: 6112206 (Open Web Text)

Max Activating Token Index: 352

Text #4

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1884. Min Act: -0.1700

Data Index: 4135891 (Open Web Text)

Max Activating Token Index: 52

Text #5

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1601. Min Act: -0.1700

Data Index: 8039934 (Open Web Text)

Max Activating Token Index: 364

Text #6

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1620. Min Act: -0.1700

Data Index: 7915093 (Open Web Text)

Max Activating Token Index: 328

Text #7

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1723. Min Act: -0.1700

Data Index: 1613656 (Open Web Text)

Max Activating Token Index: 482

Text #8

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1784. Min Act: -0.1700

Data Index: 84847 (Open Web Text)

Max Activating Token Index: 369

Text #9

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1573. Min Act: -0.1700

Data Index: 7892982 (Open Web Text)

Max Activating Token Index: 316

Text #10

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1794. Min Act: -0.1700

Data Index: 7661155 (Open Web Text)

Max Activating Token Index: 383

Text #11

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1817. Min Act: -0.1700

Data Index: 7427946 (Open Web Text)

Max Activating Token Index: 525

Text #12

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1634. Min Act: -0.1700

Data Index: 1461174 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1911. Min Act: -0.1700

Data Index: 4913115 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1744. Min Act: -0.1700

Data Index: 4815764 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1684. Min Act: -0.1700

Data Index: 4771245 (Open Web Text)

Max Activating Token Index: 415

Text #16

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1682. Min Act: -0.1700

Data Index: 4250426 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1653. Min Act: -0.1700

Data Index: 679581 (Open Web Text)

Max Activating Token Index: 316

Text #18

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1296. Min Act: -0.1700

Data Index: 1887538 (Open Web Text)

Max Activating Token Index: 527

Text #19

Max Range: 5.2183. Min Range: -5.2183

Max Act: 5.1679. Min Act: -0.1700

Data Index: 1987660 (Open Web Text)

Max Activating Token Index: 304