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

Dataset: Open Web Text

Neuron 655 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: 3.8355. Min Range: -3.8355

Max Act: 3.8355. Min Act: -0.1700

Data Index: 7735364 (Open Web Text)

Max Activating Token Index: 303

Text #1

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.8022. Min Act: -0.1700

Data Index: 1562278 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.7957. Min Act: -0.1700

Data Index: 8626558 (Open Web Text)

Max Activating Token Index: 222

Text #3

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.7587. Min Act: -0.1700

Data Index: 4873751 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.7856. Min Act: -0.1700

Data Index: 5702986 (Open Web Text)

Max Activating Token Index: 911

Text #5

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.7288. Min Act: -0.1700

Data Index: 4165922 (Open Web Text)

Max Activating Token Index: 468

Text #6

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6993. Min Act: -0.1700

Data Index: 226431 (Open Web Text)

Max Activating Token Index: 805

Text #7

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.7265. Min Act: -0.1700

Data Index: 4185002 (Open Web Text)

Max Activating Token Index: 249

Text #8

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6906. Min Act: -0.1700

Data Index: 2275208 (Open Web Text)

Max Activating Token Index: 695

Text #9

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.7340. Min Act: -0.1700

Data Index: 7510287 (Open Web Text)

Max Activating Token Index: 769

Text #10

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6941. Min Act: -0.1700

Data Index: 1752006 (Open Web Text)

Max Activating Token Index: 440

Text #11

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6595. Min Act: -0.1700

Data Index: 2098135 (Open Web Text)

Max Activating Token Index: 182

Text #12

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6985. Min Act: -0.1700

Data Index: 7485423 (Open Web Text)

Max Activating Token Index: 720

Text #13

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6686. Min Act: -0.1700

Data Index: 3029279 (Open Web Text)

Max Activating Token Index: 452

Text #14

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6685. Min Act: -0.1700

Data Index: 8624436 (Open Web Text)

Max Activating Token Index: 798

Text #15

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6866. Min Act: -0.1700

Data Index: 2501883 (Open Web Text)

Max Activating Token Index: 595

Text #16

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6563. Min Act: -0.1700

Data Index: 6784235 (Open Web Text)

Max Activating Token Index: 194

Text #17

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6152. Min Act: -0.1700

Data Index: 426324 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6358. Min Act: -0.1700

Data Index: 7553459 (Open Web Text)

Max Activating Token Index: 943

Text #19

Max Range: 3.8355. Min Range: -3.8355

Max Act: 3.6308. Min Act: -0.1700

Data Index: 2598920 (Open Web Text)

Max Activating Token Index: 124