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

Dataset: Open Web Text

Neuron 1750 in Layer 0

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: 3.2952. Min Range: -3.2952

Max Act: 3.2952. Min Act: -0.1700

Data Index: 6143048 (Open Web Text)

Max Activating Token Index: 919

Text #1

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.2394. Min Act: -0.1679

Data Index: 2994104 (Open Web Text)

Max Activating Token Index: 446

Text #2

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1872. Min Act: -0.1679

Data Index: 654817 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1487. Min Act: -0.1686

Data Index: 5175754 (Open Web Text)

Max Activating Token Index: 146

Text #4

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1316. Min Act: -0.1700

Data Index: 6315721 (Open Web Text)

Max Activating Token Index: 998

Text #5

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1494. Min Act: -0.1700

Data Index: 8498775 (Open Web Text)

Max Activating Token Index: 1017

Text #6

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1476. Min Act: -0.1679

Data Index: 6315738 (Open Web Text)

Max Activating Token Index: 575

Text #7

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1346. Min Act: -0.1679

Data Index: 8498777 (Open Web Text)

Max Activating Token Index: 562

Text #8

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1248. Min Act: -0.1679

Data Index: 6315740 (Open Web Text)

Max Activating Token Index: 248

Text #9

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1281. Min Act: -0.1700

Data Index: 4219346 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1340. Min Act: -0.1679

Data Index: 6143051 (Open Web Text)

Max Activating Token Index: 656

Text #11

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1325. Min Act: -0.1682

Data Index: 6143050 (Open Web Text)

Max Activating Token Index: 934

Text #12

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1279. Min Act: -0.1700

Data Index: 1521232 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1140. Min Act: -0.1700

Data Index: 1014641 (Open Web Text)

Max Activating Token Index: 166

Text #14

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1012. Min Act: -0.1679

Data Index: 6143049 (Open Web Text)

Max Activating Token Index: 823

Text #15

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1156. Min Act: -0.1697

Data Index: 654818 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.1023. Min Act: -0.1700

Data Index: 1886713 (Open Web Text)

Max Activating Token Index: 216

Text #17

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.0832. Min Act: -0.1694

Data Index: 4528889 (Open Web Text)

Max Activating Token Index: 791

Text #18

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.0814. Min Act: -0.1700

Data Index: 1521230 (Open Web Text)

Max Activating Token Index: 152

Text #19

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.0929. Min Act: -0.1700

Data Index: 8029470 (Open Web Text)

Max Activating Token Index: 54