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

Dataset: Open Web Text

Neuron 2191 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: 1.9920. Min Range: -1.9920

Max Act: 1.9920. Min Act: -0.1700

Data Index: 4409151 (Open Web Text)

Max Activating Token Index: 1020

Text #1

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9458. Min Act: -0.1699

Data Index: 2934250 (Open Web Text)

Max Activating Token Index: 983

Text #2

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9541. Min Act: -0.1700

Data Index: 4461036 (Open Web Text)

Max Activating Token Index: 629

Text #3

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9558. Min Act: -0.1700

Data Index: 121141 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9574. Min Act: -0.1700

Data Index: 4404617 (Open Web Text)

Max Activating Token Index: 126

Text #5

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9554. Min Act: -0.1700

Data Index: 2081634 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9528. Min Act: -0.1700

Data Index: 6062781 (Open Web Text)

Max Activating Token Index: 559

Text #7

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9335. Min Act: -0.1700

Data Index: 6064622 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9392. Min Act: -0.1700

Data Index: 8772884 (Open Web Text)

Max Activating Token Index: 744

Text #9

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9299. Min Act: -0.1700

Data Index: 4344606 (Open Web Text)

Max Activating Token Index: 247

Text #10

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9176. Min Act: -0.1700

Data Index: 6553698 (Open Web Text)

Max Activating Token Index: 398

Text #11

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9215. Min Act: -0.1700

Data Index: 6145818 (Open Web Text)

Max Activating Token Index: 499

Text #12

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9428. Min Act: -0.1700

Data Index: 1509947 (Open Web Text)

Max Activating Token Index: 703

Text #13

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9287. Min Act: -0.1700

Data Index: 887752 (Open Web Text)

Max Activating Token Index: 672

Text #14

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9328. Min Act: -0.1700

Data Index: 5547746 (Open Web Text)

Max Activating Token Index: 902

Text #15

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9352. Min Act: -0.1697

Data Index: 3444696 (Open Web Text)

Max Activating Token Index: 378

Text #16

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9236. Min Act: -0.1700

Data Index: 813537 (Open Web Text)

Max Activating Token Index: 791

Text #17

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9377. Min Act: -0.1700

Data Index: 767641 (Open Web Text)

Max Activating Token Index: 127

Text #18

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9302. Min Act: -0.1700

Data Index: 5316946 (Open Web Text)

Max Activating Token Index: 443

Text #19

Max Range: 1.9920. Min Range: -1.9920

Max Act: 1.9357. Min Act: -0.1700

Data Index: 4753965 (Open Web Text)

Max Activating Token Index: 369