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

Dataset: Open Web Text

Neuron 1577 in Layer 4

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: 4.0882. Min Range: -4.0882

Max Act: 4.0882. Min Act: -0.1700

Data Index: 5419702 (Open Web Text)

Max Activating Token Index: 580

Text #1

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9512. Min Act: -0.1700

Data Index: 1430713 (Open Web Text)

Max Activating Token Index: 459

Text #2

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9471. Min Act: -0.1700

Data Index: 4180630 (Open Web Text)

Max Activating Token Index: 278

Text #3

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9344. Min Act: -0.1700

Data Index: 6583625 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9328. Min Act: -0.1700

Data Index: 2428076 (Open Web Text)

Max Activating Token Index: 519

Text #5

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9201. Min Act: -0.1700

Data Index: 6531164 (Open Web Text)

Max Activating Token Index: 489

Text #6

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8740. Min Act: -0.1700

Data Index: 7936681 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8954. Min Act: -0.1700

Data Index: 1584390 (Open Web Text)

Max Activating Token Index: 333

Text #8

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8338. Min Act: -0.1700

Data Index: 7966412 (Open Web Text)

Max Activating Token Index: 412

Text #9

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8266. Min Act: -0.1700

Data Index: 4180631 (Open Web Text)

Max Activating Token Index: 696

Text #10

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8477. Min Act: -0.1700

Data Index: 8648982 (Open Web Text)

Max Activating Token Index: 520

Text #11

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8200. Min Act: -0.1700

Data Index: 3809784 (Open Web Text)

Max Activating Token Index: 733

Text #12

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.7963. Min Act: -0.1700

Data Index: 1463490 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.7468. Min Act: -0.1700

Data Index: 6972821 (Open Web Text)

Max Activating Token Index: 972

Text #14

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.7735. Min Act: -0.1700

Data Index: 5858329 (Open Web Text)

Max Activating Token Index: 667

Text #15

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.7658. Min Act: -0.1700

Data Index: 1243036 (Open Web Text)

Max Activating Token Index: 815

Text #16

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.7606. Min Act: -0.1700

Data Index: 6938067 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.7281. Min Act: -0.1700

Data Index: 1365710 (Open Web Text)

Max Activating Token Index: 527

Text #18

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.7864. Min Act: -0.1700

Data Index: 7251430 (Open Web Text)

Max Activating Token Index: 523

Text #19

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.7979. Min Act: -0.1700

Data Index: 7576860 (Open Web Text)

Max Activating Token Index: 356