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

Dataset: Open Web Text

Neuron 2836 in Layer 0

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: 1.5670. Min Range: -1.5670

Max Act: 1.5670. Min Act: -0.1683

Data Index: 4616261 (Open Web Text)

Max Activating Token Index: 850

Text #1

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5430. Min Act: -0.1019

Data Index: 906835 (Open Web Text)

Max Activating Token Index: 767

Text #2

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5394. Min Act: -0.0456

Data Index: 1393390 (Open Web Text)

Max Activating Token Index: 526

Text #3

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5293. Min Act: -0.1108

Data Index: 8792428 (Open Web Text)

Max Activating Token Index: 490

Text #4

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5349. Min Act: -0.1084

Data Index: 24385 (Open Web Text)

Max Activating Token Index: 807

Text #5

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5253. Min Act: -0.1460

Data Index: 1643496 (Open Web Text)

Max Activating Token Index: 361

Text #6

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5202. Min Act: -0.0694

Data Index: 1658855 (Open Web Text)

Max Activating Token Index: 727

Text #7

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5178. Min Act: -0.1455

Data Index: 4379496 (Open Web Text)

Max Activating Token Index: 607

Text #8

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5256. Min Act: -0.1520

Data Index: 232476 (Open Web Text)

Max Activating Token Index: 731

Text #9

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5177. Min Act: -0.1106

Data Index: 910826 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5122. Min Act: -0.1038

Data Index: 219447 (Open Web Text)

Max Activating Token Index: 739

Text #11

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5093. Min Act: -0.1431

Data Index: 5217355 (Open Web Text)

Max Activating Token Index: 717

Text #12

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5134. Min Act: -0.0346

Data Index: 6228242 (Open Web Text)

Max Activating Token Index: 372

Text #13

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5132. Min Act: -0.0488

Data Index: 6444101 (Open Web Text)

Max Activating Token Index: 341

Text #14

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5089. Min Act: -0.0778

Data Index: 26510 (Open Web Text)

Max Activating Token Index: 797

Text #15

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5031. Min Act: -0.0955

Data Index: 8784373 (Open Web Text)

Max Activating Token Index: 377

Text #16

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5077. Min Act: -0.1512

Data Index: 5419006 (Open Web Text)

Max Activating Token Index: 825

Text #17

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5076. Min Act: -0.1341

Data Index: 4906836 (Open Web Text)

Max Activating Token Index: 862

Text #18

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5067. Min Act: -0.0713

Data Index: 3448917 (Open Web Text)

Max Activating Token Index: 765

Text #19

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5046. Min Act: -0.0381

Data Index: 1380670 (Open Web Text)

Max Activating Token Index: 556