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

Dataset: Open Web Text

Neuron 613 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: 5.3211. Min Range: -5.3211

Max Act: 5.2969. Min Act: -0.1700

Data Index: 3503961 (Open Web Text)

Max Activating Token Index: 535

Text #1

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.3211. Min Act: -0.1700

Data Index: 3712609 (Open Web Text)

Max Activating Token Index: 680

Text #2

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1967. Min Act: -0.1700

Data Index: 2198656 (Open Web Text)

Max Activating Token Index: 371

Text #3

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.2430. Min Act: -0.1700

Data Index: 716339 (Open Web Text)

Max Activating Token Index: 797

Text #4

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1795. Min Act: -0.1700

Data Index: 1148676 (Open Web Text)

Max Activating Token Index: 969

Text #5

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1397. Min Act: -0.1700

Data Index: 8622277 (Open Web Text)

Max Activating Token Index: 963

Text #6

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1453. Min Act: -0.1700

Data Index: 7763237 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1338. Min Act: -0.1700

Data Index: 3728244 (Open Web Text)

Max Activating Token Index: 990

Text #8

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1329. Min Act: -0.1700

Data Index: 4736860 (Open Web Text)

Max Activating Token Index: 907

Text #9

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1029. Min Act: -0.1700

Data Index: 6152571 (Open Web Text)

Max Activating Token Index: 1017

Text #10

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.0785. Min Act: -0.1700

Data Index: 2682346 (Open Web Text)

Max Activating Token Index: 359

Text #11

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1547. Min Act: -0.1700

Data Index: 3689047 (Open Web Text)

Max Activating Token Index: 805

Text #12

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.0492. Min Act: -0.1700

Data Index: 6539090 (Open Web Text)

Max Activating Token Index: 915

Text #13

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1106. Min Act: -0.1700

Data Index: 6727657 (Open Web Text)

Max Activating Token Index: 709

Text #14

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1097. Min Act: -0.1700

Data Index: 7878371 (Open Web Text)

Max Activating Token Index: 324

Text #15

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1061. Min Act: -0.1700

Data Index: 3156757 (Open Web Text)

Max Activating Token Index: 515

Text #16

Max Range: 5.3211. Min Range: -5.3211

Max Act: 4.9975. Min Act: -0.1700

Data Index: 688521 (Open Web Text)

Max Activating Token Index: 902

Text #17

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.0669. Min Act: -0.1700

Data Index: 1416655 (Open Web Text)

Max Activating Token Index: 901

Text #18

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.1207. Min Act: -0.1700

Data Index: 508597 (Open Web Text)

Max Activating Token Index: 194

Text #19

Max Range: 5.3211. Min Range: -5.3211

Max Act: 5.0451. Min Act: -0.1700

Data Index: 5718522 (Open Web Text)

Max Activating Token Index: 271