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

Dataset: Open Web Text

Neuron 2625 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: 1.6702. Min Range: -1.6702

Max Act: 1.6702. Min Act: -0.1700

Data Index: 1683616 (Open Web Text)

Max Activating Token Index: 181

Text #1

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6687. Min Act: -0.1700

Data Index: 2069841 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6588. Min Act: -0.1700

Data Index: 7255449 (Open Web Text)

Max Activating Token Index: 687

Text #3

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6583. Min Act: -0.1700

Data Index: 7559535 (Open Web Text)

Max Activating Token Index: 182

Text #4

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6289. Min Act: -0.1700

Data Index: 4485374 (Open Web Text)

Max Activating Token Index: 41

Text #5

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6232. Min Act: -0.1700

Data Index: 6660663 (Open Web Text)

Max Activating Token Index: 601

Text #6

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6122. Min Act: -0.1700

Data Index: 2368205 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6107. Min Act: -0.1700

Data Index: 2894141 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6087. Min Act: -0.1700

Data Index: 5906199 (Open Web Text)

Max Activating Token Index: 815

Text #9

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6128. Min Act: -0.1700

Data Index: 4977208 (Open Web Text)

Max Activating Token Index: 290

Text #10

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6041. Min Act: -0.1700

Data Index: 1734657 (Open Web Text)

Max Activating Token Index: 888

Text #11

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6017. Min Act: -0.1700

Data Index: 1752251 (Open Web Text)

Max Activating Token Index: 641

Text #12

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6078. Min Act: -0.1700

Data Index: 8828576 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6063. Min Act: -0.1700

Data Index: 1967159 (Open Web Text)

Max Activating Token Index: 554

Text #14

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6034. Min Act: -0.1700

Data Index: 6957999 (Open Web Text)

Max Activating Token Index: 790

Text #15

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.5985. Min Act: -0.1700

Data Index: 1400654 (Open Web Text)

Max Activating Token Index: 349

Text #16

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6002. Min Act: -0.1699

Data Index: 8121625 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6079. Min Act: -0.1700

Data Index: 4090930 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.5987. Min Act: -0.1700

Data Index: 3082014 (Open Web Text)

Max Activating Token Index: 703

Text #19

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.5988. Min Act: -0.1698

Data Index: 1203886 (Open Web Text)

Max Activating Token Index: 927