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

Dataset: Open Web Text

Neuron 60 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: 2.3781. Min Range: -2.3781

Max Act: 2.3636. Min Act: -0.1699

Data Index: 2910347 (Open Web Text)

Max Activating Token Index: 71

Text #1

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.3781. Min Act: -0.1700

Data Index: 5907991 (Open Web Text)

Max Activating Token Index: 871

Text #2

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.3532. Min Act: -0.1700

Data Index: 2240592 (Open Web Text)

Max Activating Token Index: 252

Text #3

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1758. Min Act: -0.1700

Data Index: 4707345 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.2681. Min Act: -0.1700

Data Index: 5455004 (Open Web Text)

Max Activating Token Index: 289

Text #5

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1380. Min Act: -0.1700

Data Index: 733810 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.2037. Min Act: -0.1700

Data Index: 1299650 (Open Web Text)

Max Activating Token Index: 87

Text #7

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.2459. Min Act: -0.1700

Data Index: 4294576 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.2204. Min Act: -0.1700

Data Index: 447661 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1976. Min Act: -0.1700

Data Index: 6941620 (Open Web Text)

Max Activating Token Index: 95

Text #10

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.2136. Min Act: -0.1700

Data Index: 595395 (Open Web Text)

Max Activating Token Index: 689

Text #11

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1774. Min Act: -0.1700

Data Index: 6512066 (Open Web Text)

Max Activating Token Index: 192

Text #12

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1960. Min Act: -0.1700

Data Index: 6012383 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1745. Min Act: -0.1700

Data Index: 1507564 (Open Web Text)

Max Activating Token Index: 370

Text #14

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1628. Min Act: -0.1700

Data Index: 2562819 (Open Web Text)

Max Activating Token Index: 270

Text #15

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1523. Min Act: -0.1700

Data Index: 1724285 (Open Web Text)

Max Activating Token Index: 600

Text #16

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1774. Min Act: -0.1700

Data Index: 6113000 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1549. Min Act: -0.1700

Data Index: 6886496 (Open Web Text)

Max Activating Token Index: 242

Text #18

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1549. Min Act: -0.1700

Data Index: 5585903 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 2.3781. Min Range: -2.3781

Max Act: 2.1407. Min Act: -0.1700

Data Index: 4544781 (Open Web Text)

Max Activating Token Index: 835