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

Dataset: Open Web Text

Neuron 916 in Layer 1

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: 3.0743. Min Range: -3.0743

Max Act: 3.0743. Min Act: -0.1700

Data Index: 4022964 (Open Web Text)

Max Activating Token Index: 667

Text #1

Max Range: 3.0743. Min Range: -3.0743

Max Act: 3.0567. Min Act: -0.1700

Data Index: 3398612 (Open Web Text)

Max Activating Token Index: 89

Text #2

Max Range: 3.0743. Min Range: -3.0743

Max Act: 3.0129. Min Act: -0.1700

Data Index: 965594 (Open Web Text)

Max Activating Token Index: 600

Text #3

Max Range: 3.0743. Min Range: -3.0743

Max Act: 3.0177. Min Act: -0.1700

Data Index: 108570 (Open Web Text)

Max Activating Token Index: 278

Text #4

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.9160. Min Act: -0.1700

Data Index: 1435706 (Open Web Text)

Max Activating Token Index: 936

Text #5

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.9230. Min Act: -0.1700

Data Index: 6930332 (Open Web Text)

Max Activating Token Index: 186

Text #6

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.9159. Min Act: -0.1700

Data Index: 4647700 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.9026. Min Act: -0.1700

Data Index: 7632401 (Open Web Text)

Max Activating Token Index: 743

Text #8

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.9256. Min Act: -0.1700

Data Index: 50727 (Open Web Text)

Max Activating Token Index: 336

Text #9

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.8999. Min Act: -0.1700

Data Index: 8806106 (Open Web Text)

Max Activating Token Index: 120

Text #10

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.9159. Min Act: -0.1700

Data Index: 4067418 (Open Web Text)

Max Activating Token Index: 372

Text #11

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.8978. Min Act: -0.1700

Data Index: 4721770 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.9024. Min Act: -0.1700

Data Index: 3283292 (Open Web Text)

Max Activating Token Index: 444

Text #13

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.8781. Min Act: -0.1700

Data Index: 7393804 (Open Web Text)

Max Activating Token Index: 261

Text #14

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.8879. Min Act: -0.1700

Data Index: 8155337 (Open Web Text)

Max Activating Token Index: 805

Text #15

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.8851. Min Act: -0.1700

Data Index: 5069515 (Open Web Text)

Max Activating Token Index: 782

Text #16

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.8742. Min Act: -0.1700

Data Index: 7950080 (Open Web Text)

Max Activating Token Index: 388

Text #17

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.8685. Min Act: -0.1700

Data Index: 54353 (Open Web Text)

Max Activating Token Index: 100

Text #18

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.8572. Min Act: -0.1700

Data Index: 5942714 (Open Web Text)

Max Activating Token Index: 760

Text #19

Max Range: 3.0743. Min Range: -3.0743

Max Act: 2.8703. Min Act: -0.1700

Data Index: 5032290 (Open Web Text)

Max Activating Token Index: 348