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

Dataset: Open Web Text

Neuron 2075 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: 2.6018. Min Range: -2.6018

Max Act: 2.6018. Min Act: -0.1698

Data Index: 3908449 (Open Web Text)

Max Activating Token Index: 79

Text #1

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.5547. Min Act: -0.1697

Data Index: 7256957 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.4870. Min Act: -0.1700

Data Index: 4346852 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.4095. Min Act: -0.1700

Data Index: 4184625 (Open Web Text)

Max Activating Token Index: 750

Text #4

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.4293. Min Act: -0.1688

Data Index: 2707763 (Open Web Text)

Max Activating Token Index: 262

Text #5

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.4237. Min Act: -0.1700

Data Index: 1986996 (Open Web Text)

Max Activating Token Index: 252

Text #6

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3980. Min Act: -0.1673

Data Index: 4111565 (Open Web Text)

Max Activating Token Index: 792

Text #7

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3771. Min Act: -0.1695

Data Index: 4515910 (Open Web Text)

Max Activating Token Index: 901

Text #8

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3999. Min Act: -0.1700

Data Index: 7757675 (Open Web Text)

Max Activating Token Index: 292

Text #9

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3532. Min Act: -0.1700

Data Index: 6833934 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3811. Min Act: -0.1695

Data Index: 4111564 (Open Web Text)

Max Activating Token Index: 996

Text #11

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3705. Min Act: -0.1689

Data Index: 8822463 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3621. Min Act: -0.1700

Data Index: 4978339 (Open Web Text)

Max Activating Token Index: 615

Text #13

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3525. Min Act: -0.1696

Data Index: 4728177 (Open Web Text)

Max Activating Token Index: 952

Text #14

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3678. Min Act: -0.1700

Data Index: 6322163 (Open Web Text)

Max Activating Token Index: 816

Text #15

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3224. Min Act: -0.1700

Data Index: 4993479 (Open Web Text)

Max Activating Token Index: 552

Text #16

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3393. Min Act: -0.1695

Data Index: 2864955 (Open Web Text)

Max Activating Token Index: 969

Text #17

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3406. Min Act: -0.1700

Data Index: 7878430 (Open Web Text)

Max Activating Token Index: 752

Text #18

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3450. Min Act: -0.1700

Data Index: 1205690 (Open Web Text)

Max Activating Token Index: 774

Text #19

Max Range: 2.6018. Min Range: -2.6018

Max Act: 2.3242. Min Act: -0.1636

Data Index: 1245140 (Open Web Text)

Max Activating Token Index: 500