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

Dataset: Open Web Text

Neuron 1403 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: 1.8712. Min Range: -1.8712

Max Act: 1.8644. Min Act: -0.1698

Data Index: 7221003 (Open Web Text)

Max Activating Token Index: 864

Text #1

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8609. Min Act: -0.1700

Data Index: 5436632 (Open Web Text)

Max Activating Token Index: 952

Text #2

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8712. Min Act: -0.1699

Data Index: 7221002 (Open Web Text)

Max Activating Token Index: 960

Text #3

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8650. Min Act: -0.1700

Data Index: 5436635 (Open Web Text)

Max Activating Token Index: 574

Text #4

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8557. Min Act: -0.1699

Data Index: 5919912 (Open Web Text)

Max Activating Token Index: 921

Text #5

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8527. Min Act: -0.1699

Data Index: 458883 (Open Web Text)

Max Activating Token Index: 999

Text #6

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8330. Min Act: -0.1700

Data Index: 5436630 (Open Web Text)

Max Activating Token Index: 934

Text #7

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8295. Min Act: -0.1699

Data Index: 1589430 (Open Web Text)

Max Activating Token Index: 671

Text #8

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8374. Min Act: -0.1700

Data Index: 2015014 (Open Web Text)

Max Activating Token Index: 921

Text #9

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8315. Min Act: -0.1700

Data Index: 3068839 (Open Web Text)

Max Activating Token Index: 907

Text #10

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8293. Min Act: -0.1700

Data Index: 5436634 (Open Web Text)

Max Activating Token Index: 616

Text #11

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8290. Min Act: -0.1697

Data Index: 4119698 (Open Web Text)

Max Activating Token Index: 614

Text #12

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8338. Min Act: -0.1700

Data Index: 5436633 (Open Web Text)

Max Activating Token Index: 1005

Text #13

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8132. Min Act: -0.1693

Data Index: 1589429 (Open Web Text)

Max Activating Token Index: 796

Text #14

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8279. Min Act: -0.1700

Data Index: 3068835 (Open Web Text)

Max Activating Token Index: 897

Text #15

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8052. Min Act: -0.1700

Data Index: 2015016 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8125. Min Act: -0.1700

Data Index: 3750614 (Open Web Text)

Max Activating Token Index: 908

Text #17

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8052. Min Act: -0.1700

Data Index: 5996328 (Open Web Text)

Max Activating Token Index: 909

Text #18

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8127. Min Act: -0.1700

Data Index: 7865339 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8146. Min Act: -0.1700

Data Index: 2015017 (Open Web Text)

Max Activating Token Index: 731