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

Dataset: Open Web Text

Neuron 1509 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: 6.3466. Min Range: -6.3466

Max Act: 6.3466. Min Act: -0.1700

Data Index: 861061 (Open Web Text)

Max Activating Token Index: 274

Text #1

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.3292. Min Act: -0.1700

Data Index: 1953079 (Open Web Text)

Max Activating Token Index: 347

Text #2

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1718. Min Act: -0.1693

Data Index: 6448237 (Open Web Text)

Max Activating Token Index: 421

Text #3

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1615. Min Act: -0.1698

Data Index: 2717260 (Open Web Text)

Max Activating Token Index: 510

Text #4

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1927. Min Act: -0.1700

Data Index: 4612760 (Open Web Text)

Max Activating Token Index: 219

Text #5

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1782. Min Act: -0.1700

Data Index: 3434293 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.2027. Min Act: -0.1700

Data Index: 1716602 (Open Web Text)

Max Activating Token Index: 469

Text #7

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.0925. Min Act: -0.1700

Data Index: 8428894 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1577. Min Act: -0.1700

Data Index: 7803130 (Open Web Text)

Max Activating Token Index: 153

Text #9

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1602. Min Act: -0.1700

Data Index: 7639610 (Open Web Text)

Max Activating Token Index: 713

Text #10

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1346. Min Act: -0.1700

Data Index: 6840639 (Open Web Text)

Max Activating Token Index: 445

Text #11

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.2130. Min Act: -0.1700

Data Index: 4517068 (Open Web Text)

Max Activating Token Index: 299

Text #12

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.0864. Min Act: -0.1700

Data Index: 5114844 (Open Web Text)

Max Activating Token Index: 195

Text #13

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1372. Min Act: -0.1700

Data Index: 4004398 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1604. Min Act: -0.1700

Data Index: 1746166 (Open Web Text)

Max Activating Token Index: 766

Text #15

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1729. Min Act: -0.1700

Data Index: 1377750 (Open Web Text)

Max Activating Token Index: 481

Text #16

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1424. Min Act: -0.1700

Data Index: 7285202 (Open Web Text)

Max Activating Token Index: 176

Text #17

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1044. Min Act: -0.1700

Data Index: 6808865 (Open Web Text)

Max Activating Token Index: 334

Text #18

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1549. Min Act: -0.1700

Data Index: 2165322 (Open Web Text)

Max Activating Token Index: 149

Text #19

Max Range: 6.3466. Min Range: -6.3466

Max Act: 6.1798. Min Act: -0.1700

Data Index: 6272155 (Open Web Text)

Max Activating Token Index: 205