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

Dataset: Open Web Text

Neuron 1656 in Layer 3

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: 5.3766. Min Range: -5.3766

Max Act: 5.3766. Min Act: -0.1700

Data Index: 1030626 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 5.3766. Min Range: -5.3766

Max Act: 5.3441. Min Act: -0.1700

Data Index: 8694858 (Open Web Text)

Max Activating Token Index: 648

Text #2

Max Range: 5.3766. Min Range: -5.3766

Max Act: 5.0742. Min Act: -0.1700

Data Index: 6605723 (Open Web Text)

Max Activating Token Index: 76

Text #3

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.9672. Min Act: -0.1700

Data Index: 33545 (Open Web Text)

Max Activating Token Index: 68

Text #4

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.9786. Min Act: -0.1700

Data Index: 6574976 (Open Web Text)

Max Activating Token Index: 215

Text #5

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.9657. Min Act: -0.1700

Data Index: 6986757 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.8576. Min Act: -0.1700

Data Index: 1389159 (Open Web Text)

Max Activating Token Index: 574

Text #7

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.9127. Min Act: -0.1700

Data Index: 5161245 (Open Web Text)

Max Activating Token Index: 700

Text #8

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.8748. Min Act: -0.1700

Data Index: 230183 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.7998. Min Act: -0.1700

Data Index: 2515115 (Open Web Text)

Max Activating Token Index: 663

Text #10

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.9298. Min Act: -0.1700

Data Index: 8148083 (Open Web Text)

Max Activating Token Index: 522

Text #11

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.8291. Min Act: -0.1700

Data Index: 4799250 (Open Web Text)

Max Activating Token Index: 934

Text #12

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.8821. Min Act: -0.1700

Data Index: 1288992 (Open Web Text)

Max Activating Token Index: 826

Text #13

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.7832. Min Act: -0.1700

Data Index: 2585554 (Open Web Text)

Max Activating Token Index: 509

Text #14

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.8367. Min Act: -0.1700

Data Index: 2515609 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.8112. Min Act: -0.1700

Data Index: 6712088 (Open Web Text)

Max Activating Token Index: 321

Text #16

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.8717. Min Act: -0.1700

Data Index: 5383902 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.8021. Min Act: -0.1700

Data Index: 143310 (Open Web Text)

Max Activating Token Index: 219

Text #18

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.8428. Min Act: -0.1700

Data Index: 3797572 (Open Web Text)

Max Activating Token Index: 612

Text #19

Max Range: 5.3766. Min Range: -5.3766

Max Act: 4.8059. Min Act: -0.1700

Data Index: 375235 (Open Web Text)

Max Activating Token Index: 632