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

Dataset: Open Web Text

Neuron 550 in Layer 6

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: 4.5514. Min Range: -4.5514

Max Act: 4.5514. Min Act: -0.1700

Data Index: 3965446 (Open Web Text)

Max Activating Token Index: 996

Text #1

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4767. Min Act: -0.1700

Data Index: 6599095 (Open Web Text)

Max Activating Token Index: 550

Text #2

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4957. Min Act: -0.1700

Data Index: 2426107 (Open Web Text)

Max Activating Token Index: 353

Text #3

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4680. Min Act: -0.1700

Data Index: 7350731 (Open Web Text)

Max Activating Token Index: 255

Text #4

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4673. Min Act: -0.1700

Data Index: 7425635 (Open Web Text)

Max Activating Token Index: 514

Text #5

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4827. Min Act: -0.1700

Data Index: 1154216 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4646. Min Act: -0.1700

Data Index: 4894683 (Open Web Text)

Max Activating Token Index: 572

Text #7

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4698. Min Act: -0.1700

Data Index: 1319722 (Open Web Text)

Max Activating Token Index: 866

Text #8

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4588. Min Act: -0.1700

Data Index: 5362757 (Open Web Text)

Max Activating Token Index: 919

Text #9

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4516. Min Act: -0.1700

Data Index: 379725 (Open Web Text)

Max Activating Token Index: 582

Text #10

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4187. Min Act: -0.1700

Data Index: 4523248 (Open Web Text)

Max Activating Token Index: 967

Text #11

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4536. Min Act: -0.1700

Data Index: 8312611 (Open Web Text)

Max Activating Token Index: 911

Text #12

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4252. Min Act: -0.1700

Data Index: 703422 (Open Web Text)

Max Activating Token Index: 371

Text #13

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.4159. Min Act: -0.1700

Data Index: 7627824 (Open Web Text)

Max Activating Token Index: 363

Text #14

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.3873. Min Act: -0.1700

Data Index: 5859765 (Open Web Text)

Max Activating Token Index: 736

Text #15

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.3897. Min Act: -0.1700

Data Index: 236120 (Open Web Text)

Max Activating Token Index: 622

Text #16

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.3423. Min Act: -0.1700

Data Index: 6467302 (Open Web Text)

Max Activating Token Index: 730

Text #17

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.3568. Min Act: -0.1700

Data Index: 3500217 (Open Web Text)

Max Activating Token Index: 434

Text #18

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.3446. Min Act: -0.1700

Data Index: 5173585 (Open Web Text)

Max Activating Token Index: 324

Text #19

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.3215. Min Act: -0.1700

Data Index: 2635058 (Open Web Text)

Max Activating Token Index: 670