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

Dataset: Open Web Text

Neuron 2588 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: 2.9032. Min Range: -2.9032

Max Act: 2.9032. Min Act: -0.1700

Data Index: 3683293 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.8018. Min Act: -0.1700

Data Index: 7791605 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7669. Min Act: -0.1700

Data Index: 5461131 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7633. Min Act: -0.1700

Data Index: 2447230 (Open Web Text)

Max Activating Token Index: 678

Text #4

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7551. Min Act: -0.1700

Data Index: 3934145 (Open Web Text)

Max Activating Token Index: 49

Text #5

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7285. Min Act: -0.1700

Data Index: 6924442 (Open Web Text)

Max Activating Token Index: 158

Text #6

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7345. Min Act: -0.1700

Data Index: 8096231 (Open Web Text)

Max Activating Token Index: 497

Text #7

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7184. Min Act: -0.1700

Data Index: 5127105 (Open Web Text)

Max Activating Token Index: 400

Text #8

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7383. Min Act: -0.1700

Data Index: 3960718 (Open Web Text)

Max Activating Token Index: 512

Text #9

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7546. Min Act: -0.1700

Data Index: 3075613 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7276. Min Act: -0.1700

Data Index: 401987 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7162. Min Act: -0.1700

Data Index: 6537058 (Open Web Text)

Max Activating Token Index: 947

Text #12

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7368. Min Act: -0.1700

Data Index: 3885925 (Open Web Text)

Max Activating Token Index: 79

Text #13

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7354. Min Act: -0.1700

Data Index: 6427485 (Open Web Text)

Max Activating Token Index: 57

Text #14

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7113. Min Act: -0.1700

Data Index: 616458 (Open Web Text)

Max Activating Token Index: 140

Text #15

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7300. Min Act: -0.1700

Data Index: 3845586 (Open Web Text)

Max Activating Token Index: 496

Text #16

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.7044. Min Act: -0.1700

Data Index: 8344146 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.6988. Min Act: -0.1700

Data Index: 5891947 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.6925. Min Act: -0.1700

Data Index: 3058482 (Open Web Text)

Max Activating Token Index: 44

Text #19

Max Range: 2.9032. Min Range: -2.9032

Max Act: 2.6928. Min Act: -0.1700

Data Index: 2213013 (Open Web Text)

Max Activating Token Index: 559