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

Dataset: Open Web Text

Neuron 1084 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: 3.3038. Min Range: -3.3038

Max Act: 3.3038. Min Act: -0.1700

Data Index: 6635500 (Open Web Text)

Max Activating Token Index: 326

Text #1

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.2429. Min Act: -0.1700

Data Index: 6802254 (Open Web Text)

Max Activating Token Index: 1001

Text #2

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1874. Min Act: -0.1700

Data Index: 4288227 (Open Web Text)

Max Activating Token Index: 398

Text #3

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1716. Min Act: -0.1700

Data Index: 721225 (Open Web Text)

Max Activating Token Index: 900

Text #4

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1821. Min Act: -0.1700

Data Index: 8032837 (Open Web Text)

Max Activating Token Index: 462

Text #5

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1769. Min Act: -0.1700

Data Index: 162947 (Open Web Text)

Max Activating Token Index: 471

Text #6

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1527. Min Act: -0.1700

Data Index: 8450956 (Open Web Text)

Max Activating Token Index: 797

Text #7

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1539. Min Act: -0.1700

Data Index: 520473 (Open Web Text)

Max Activating Token Index: 484

Text #8

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1511. Min Act: -0.1700

Data Index: 3475875 (Open Web Text)

Max Activating Token Index: 528

Text #9

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1217. Min Act: -0.1700

Data Index: 3670257 (Open Web Text)

Max Activating Token Index: 143

Text #10

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1158. Min Act: -0.1700

Data Index: 6979129 (Open Web Text)

Max Activating Token Index: 184

Text #11

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1189. Min Act: -0.1700

Data Index: 6726616 (Open Web Text)

Max Activating Token Index: 166

Text #12

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.0825. Min Act: -0.1700

Data Index: 6090938 (Open Web Text)

Max Activating Token Index: 433

Text #13

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1072. Min Act: -0.1700

Data Index: 2097454 (Open Web Text)

Max Activating Token Index: 563

Text #14

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.0939. Min Act: -0.1700

Data Index: 7108426 (Open Web Text)

Max Activating Token Index: 540

Text #15

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1115. Min Act: -0.1700

Data Index: 5530387 (Open Web Text)

Max Activating Token Index: 684

Text #16

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1101. Min Act: -0.1700

Data Index: 2324393 (Open Web Text)

Max Activating Token Index: 662

Text #17

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1116. Min Act: -0.1700

Data Index: 8610994 (Open Web Text)

Max Activating Token Index: 421

Text #18

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.1007. Min Act: -0.1700

Data Index: 8233438 (Open Web Text)

Max Activating Token Index: 320

Text #19

Max Range: 3.3038. Min Range: -3.3038

Max Act: 3.0924. Min Act: -0.1700

Data Index: 8642461 (Open Web Text)

Max Activating Token Index: 662