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

Dataset: Open Web Text

Neuron 2496 in Layer 3

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: 2.7651. Min Range: -2.7651

Max Act: 2.7587. Min Act: -0.1700

Data Index: 5456632 (Open Web Text)

Max Activating Token Index: 309

Text #1

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.7651. Min Act: -0.1700

Data Index: 4043370 (Open Web Text)

Max Activating Token Index: 910

Text #2

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.7460. Min Act: -0.1700

Data Index: 6791103 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.7168. Min Act: -0.1700

Data Index: 8387293 (Open Web Text)

Max Activating Token Index: 297

Text #4

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.7385. Min Act: -0.1700

Data Index: 8489923 (Open Web Text)

Max Activating Token Index: 882

Text #5

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6891. Min Act: -0.1700

Data Index: 7827427 (Open Web Text)

Max Activating Token Index: 347

Text #6

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6646. Min Act: -0.1700

Data Index: 8349374 (Open Web Text)

Max Activating Token Index: 866

Text #7

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6675. Min Act: -0.1700

Data Index: 2669248 (Open Web Text)

Max Activating Token Index: 292

Text #8

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6354. Min Act: -0.1700

Data Index: 1702452 (Open Web Text)

Max Activating Token Index: 905

Text #9

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6489. Min Act: -0.1700

Data Index: 4434371 (Open Web Text)

Max Activating Token Index: 348

Text #10

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6620. Min Act: -0.1700

Data Index: 3915191 (Open Web Text)

Max Activating Token Index: 308

Text #11

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6498. Min Act: -0.1700

Data Index: 742038 (Open Web Text)

Max Activating Token Index: 888

Text #12

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6450. Min Act: -0.1700

Data Index: 922410 (Open Web Text)

Max Activating Token Index: 332

Text #13

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6290. Min Act: -0.1700

Data Index: 8584874 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.5969. Min Act: -0.1700

Data Index: 8164932 (Open Web Text)

Max Activating Token Index: 932

Text #15

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6253. Min Act: -0.1700

Data Index: 7908235 (Open Web Text)

Max Activating Token Index: 272

Text #16

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6489. Min Act: -0.1700

Data Index: 6021669 (Open Web Text)

Max Activating Token Index: 273

Text #17

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.5892. Min Act: -0.1700

Data Index: 6007557 (Open Web Text)

Max Activating Token Index: 888

Text #18

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6430. Min Act: -0.1700

Data Index: 7809426 (Open Web Text)

Max Activating Token Index: 903

Text #19

Max Range: 2.7651. Min Range: -2.7651

Max Act: 2.6185. Min Act: -0.1700

Data Index: 7691342 (Open Web Text)

Max Activating Token Index: 305