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

Dataset: Open Web Text

Neuron 2227 in Layer 6

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: 4.2434. Min Range: -4.2434

Max Act: 4.2434. Min Act: -0.1700

Data Index: 2309525 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.2155. Min Act: -0.1700

Data Index: 368864 (Open Web Text)

Max Activating Token Index: 206

Text #2

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.2118. Min Act: -0.1700

Data Index: 5597296 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.2321. Min Act: -0.1700

Data Index: 1397724 (Open Web Text)

Max Activating Token Index: 791

Text #4

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.2082. Min Act: -0.1700

Data Index: 3116531 (Open Web Text)

Max Activating Token Index: 962

Text #5

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.2052. Min Act: -0.1700

Data Index: 3619716 (Open Web Text)

Max Activating Token Index: 554

Text #6

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1735. Min Act: -0.1700

Data Index: 5648801 (Open Web Text)

Max Activating Token Index: 903

Text #7

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1825. Min Act: -0.1700

Data Index: 8223792 (Open Web Text)

Max Activating Token Index: 79

Text #8

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1538. Min Act: -0.1700

Data Index: 7559177 (Open Web Text)

Max Activating Token Index: 1017

Text #9

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1559. Min Act: -0.1700

Data Index: 2175116 (Open Web Text)

Max Activating Token Index: 484

Text #10

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1706. Min Act: -0.1700

Data Index: 5577467 (Open Web Text)

Max Activating Token Index: 472

Text #11

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1776. Min Act: -0.1700

Data Index: 8084884 (Open Web Text)

Max Activating Token Index: 810

Text #12

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1404. Min Act: -0.1700

Data Index: 6762831 (Open Web Text)

Max Activating Token Index: 336

Text #13

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1052. Min Act: -0.1700

Data Index: 1807096 (Open Web Text)

Max Activating Token Index: 57

Text #14

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1203. Min Act: -0.1700

Data Index: 3750373 (Open Web Text)

Max Activating Token Index: 376

Text #15

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1253. Min Act: -0.1700

Data Index: 7154824 (Open Web Text)

Max Activating Token Index: 644

Text #16

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1521. Min Act: -0.1700

Data Index: 619191 (Open Web Text)

Max Activating Token Index: 125

Text #17

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1291. Min Act: -0.1700

Data Index: 7867288 (Open Web Text)

Max Activating Token Index: 654

Text #18

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1194. Min Act: -0.1700

Data Index: 3421256 (Open Web Text)

Max Activating Token Index: 243

Text #19

Max Range: 4.2434. Min Range: -4.2434

Max Act: 4.1303. Min Act: -0.1700

Data Index: 4137454 (Open Web Text)

Max Activating Token Index: 723