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

Dataset: Open Web Text

Neuron 452 in Layer 2

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: 3.3192. Min Range: -3.3192

Max Act: 3.3105. Min Act: -0.1700

Data Index: 8802199 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.3192. Min Act: -0.1700

Data Index: 2445097 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2864. Min Act: -0.1700

Data Index: 8290682 (Open Web Text)

Max Activating Token Index: 527

Text #3

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2657. Min Act: -0.1700

Data Index: 7416266 (Open Web Text)

Max Activating Token Index: 564

Text #4

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.1621. Min Act: -0.1700

Data Index: 2708323 (Open Web Text)

Max Activating Token Index: 57

Text #5

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.1612. Min Act: -0.1700

Data Index: 8821149 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.1236. Min Act: -0.1700

Data Index: 4800549 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.1016. Min Act: -0.1700

Data Index: 8350887 (Open Web Text)

Max Activating Token Index: 390

Text #8

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0943. Min Act: -0.1700

Data Index: 5184090 (Open Web Text)

Max Activating Token Index: 481

Text #9

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0463. Min Act: -0.1700

Data Index: 3712688 (Open Web Text)

Max Activating Token Index: 768

Text #10

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0473. Min Act: -0.1700

Data Index: 8218924 (Open Web Text)

Max Activating Token Index: 230

Text #11

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0571. Min Act: -0.1700

Data Index: 2163282 (Open Web Text)

Max Activating Token Index: 620

Text #12

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0396. Min Act: -0.1700

Data Index: 1861015 (Open Web Text)

Max Activating Token Index: 77

Text #13

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0371. Min Act: -0.1700

Data Index: 7950246 (Open Web Text)

Max Activating Token Index: 195

Text #14

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0144. Min Act: -0.1700

Data Index: 8137412 (Open Web Text)

Max Activating Token Index: 160

Text #15

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0162. Min Act: -0.1700

Data Index: 3091877 (Open Web Text)

Max Activating Token Index: 42

Text #16

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0260. Min Act: -0.1700

Data Index: 4331414 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0204. Min Act: -0.1700

Data Index: 934736 (Open Web Text)

Max Activating Token Index: 570

Text #18

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.0032. Min Act: -0.1700

Data Index: 6117992 (Open Web Text)

Max Activating Token Index: 714

Text #19

Max Range: 3.3192. Min Range: -3.3192

Max Act: 2.9684. Min Act: -0.1700

Data Index: 2396266 (Open Web Text)

Max Activating Token Index: 899