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

Dataset: Open Web Text

Neuron 754 in Layer 1

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: 1.6458. Min Range: -1.6458

Max Act: 1.6458. Min Act: -0.1700

Data Index: 5265776 (Open Web Text)

Max Activating Token Index: 184

Text #1

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6397. Min Act: -0.1700

Data Index: 2757149 (Open Web Text)

Max Activating Token Index: 776

Text #2

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6146. Min Act: -0.1700

Data Index: 3525165 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6282. Min Act: -0.1696

Data Index: 1437252 (Open Web Text)

Max Activating Token Index: 987

Text #4

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6142. Min Act: -0.1700

Data Index: 5888528 (Open Web Text)

Max Activating Token Index: 346

Text #5

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6098. Min Act: -0.1700

Data Index: 3271529 (Open Web Text)

Max Activating Token Index: 135

Text #6

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6009. Min Act: -0.1700

Data Index: 741048 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6033. Min Act: -0.1700

Data Index: 1415361 (Open Web Text)

Max Activating Token Index: 817

Text #8

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6104. Min Act: -0.1660

Data Index: 4339971 (Open Web Text)

Max Activating Token Index: 257

Text #9

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6117. Min Act: -0.1700

Data Index: 5390475 (Open Web Text)

Max Activating Token Index: 682

Text #10

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6022. Min Act: -0.1694

Data Index: 1434613 (Open Web Text)

Max Activating Token Index: 584

Text #11

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.5940. Min Act: -0.1569

Data Index: 2463626 (Open Web Text)

Max Activating Token Index: 887

Text #12

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.5921. Min Act: -0.1693

Data Index: 7415563 (Open Web Text)

Max Activating Token Index: 884

Text #13

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.5912. Min Act: -0.1700

Data Index: 4135979 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.5950. Min Act: -0.1634

Data Index: 6251997 (Open Web Text)

Max Activating Token Index: 530

Text #15

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.5937. Min Act: -0.1700

Data Index: 5696047 (Open Web Text)

Max Activating Token Index: 982

Text #16

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.5774. Min Act: -0.1683

Data Index: 5143613 (Open Web Text)

Max Activating Token Index: 936

Text #17

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.5934. Min Act: -0.1700

Data Index: 2823986 (Open Web Text)

Max Activating Token Index: 853

Text #18

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.5803. Min Act: -0.1693

Data Index: 2305159 (Open Web Text)

Max Activating Token Index: 516

Text #19

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.5822. Min Act: -0.1695

Data Index: 125865 (Open Web Text)

Max Activating Token Index: 577