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

Dataset: Open Web Text

Neuron 2009 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: 3.4321. Min Range: -3.4321

Max Act: 3.4321. Min Act: -0.1700

Data Index: 6262142 (Open Web Text)

Max Activating Token Index: 108

Text #1

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3980. Min Act: -0.1700

Data Index: 6150148 (Open Web Text)

Max Activating Token Index: 675

Text #2

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3368. Min Act: -0.1700

Data Index: 3987343 (Open Web Text)

Max Activating Token Index: 495

Text #3

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3258. Min Act: -0.1700

Data Index: 680945 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2336. Min Act: -0.1700

Data Index: 5307300 (Open Web Text)

Max Activating Token Index: 46

Text #5

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2417. Min Act: -0.1700

Data Index: 8330459 (Open Web Text)

Max Activating Token Index: 317

Text #6

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2179. Min Act: -0.1700

Data Index: 7730327 (Open Web Text)

Max Activating Token Index: 81

Text #7

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2337. Min Act: -0.1700

Data Index: 5375464 (Open Web Text)

Max Activating Token Index: 420

Text #8

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2284. Min Act: -0.1700

Data Index: 1528076 (Open Web Text)

Max Activating Token Index: 643

Text #9

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2341. Min Act: -0.1700

Data Index: 7434154 (Open Web Text)

Max Activating Token Index: 285

Text #10

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2065. Min Act: -0.1700

Data Index: 7673725 (Open Web Text)

Max Activating Token Index: 173

Text #11

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2072. Min Act: -0.1700

Data Index: 1043516 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1908. Min Act: -0.1700

Data Index: 8071672 (Open Web Text)

Max Activating Token Index: 835

Text #13

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1768. Min Act: -0.1700

Data Index: 6265438 (Open Web Text)

Max Activating Token Index: 318

Text #14

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1827. Min Act: -0.1700

Data Index: 4648202 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1563. Min Act: -0.1700

Data Index: 8416922 (Open Web Text)

Max Activating Token Index: 209

Text #16

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1651. Min Act: -0.1700

Data Index: 2157414 (Open Web Text)

Max Activating Token Index: 514

Text #17

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1573. Min Act: -0.1700

Data Index: 2652238 (Open Web Text)

Max Activating Token Index: 429

Text #18

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1718. Min Act: -0.1700

Data Index: 1538675 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.1751. Min Act: -0.1700

Data Index: 4823500 (Open Web Text)

Max Activating Token Index: 548