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

Dataset: Open Web Text

Neuron 2331 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: 1.1392. Min Range: -1.1392

Max Act: 1.1287. Min Act: -0.1700

Data Index: 7800901 (Open Web Text)

Max Activating Token Index: 290

Text #1

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.1392. Min Act: -0.1700

Data Index: 7590335 (Open Web Text)

Max Activating Token Index: 144

Text #2

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.1102. Min Act: -0.1700

Data Index: 3106306 (Open Web Text)

Max Activating Token Index: 219

Text #3

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.1099. Min Act: -0.1700

Data Index: 3356062 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.1154. Min Act: -0.1700

Data Index: 7762942 (Open Web Text)

Max Activating Token Index: 246

Text #5

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.1008. Min Act: -0.1700

Data Index: 3662159 (Open Web Text)

Max Activating Token Index: 988

Text #6

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0991. Min Act: -0.1700

Data Index: 4661618 (Open Web Text)

Max Activating Token Index: 134

Text #7

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0991. Min Act: -0.1700

Data Index: 4813144 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0751. Min Act: -0.1699

Data Index: 1825074 (Open Web Text)

Max Activating Token Index: 866

Text #9

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0745. Min Act: -0.1696

Data Index: 3281783 (Open Web Text)

Max Activating Token Index: 370

Text #10

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0612. Min Act: -0.1700

Data Index: 1123956 (Open Web Text)

Max Activating Token Index: 317

Text #11

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0753. Min Act: -0.1700

Data Index: 4126433 (Open Web Text)

Max Activating Token Index: 158

Text #12

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0660. Min Act: -0.1700

Data Index: 8081383 (Open Web Text)

Max Activating Token Index: 211

Text #13

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0768. Min Act: -0.1700

Data Index: 1152340 (Open Web Text)

Max Activating Token Index: 620

Text #14

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0594. Min Act: -0.1699

Data Index: 4813142 (Open Web Text)

Max Activating Token Index: 28

Text #15

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0602. Min Act: -0.1700

Data Index: 2663168 (Open Web Text)

Max Activating Token Index: 305

Text #16

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0511. Min Act: -0.1700

Data Index: 5406682 (Open Web Text)

Max Activating Token Index: 781

Text #17

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0532. Min Act: -0.1700

Data Index: 4305373 (Open Web Text)

Max Activating Token Index: 40

Text #18

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0583. Min Act: -0.1700

Data Index: 7444102 (Open Web Text)

Max Activating Token Index: 109

Text #19

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0416. Min Act: -0.1700

Data Index: 4683885 (Open Web Text)

Max Activating Token Index: 976