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

Dataset: Open Web Text

Neuron 852 in Layer 4

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: 3.9933. Min Range: -3.9933

Max Act: 3.9933. Min Act: -0.1700

Data Index: 1911660 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.8429. Min Act: -0.1700

Data Index: 6538761 (Open Web Text)

Max Activating Token Index: 724

Text #2

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.8611. Min Act: -0.1700

Data Index: 880684 (Open Web Text)

Max Activating Token Index: 490

Text #3

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.7118. Min Act: -0.1700

Data Index: 3882088 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.6899. Min Act: -0.1700

Data Index: 6552083 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.7525. Min Act: -0.1700

Data Index: 7233240 (Open Web Text)

Max Activating Token Index: 991

Text #6

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.6671. Min Act: -0.1700

Data Index: 7229564 (Open Web Text)

Max Activating Token Index: 336

Text #7

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.6682. Min Act: -0.1700

Data Index: 2712684 (Open Web Text)

Max Activating Token Index: 634

Text #8

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.6126. Min Act: -0.1700

Data Index: 6919678 (Open Web Text)

Max Activating Token Index: 920

Text #9

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.6088. Min Act: -0.1700

Data Index: 4166447 (Open Web Text)

Max Activating Token Index: 591

Text #10

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.6094. Min Act: -0.1700

Data Index: 1129815 (Open Web Text)

Max Activating Token Index: 702

Text #11

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.6368. Min Act: -0.1700

Data Index: 7550148 (Open Web Text)

Max Activating Token Index: 911

Text #12

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.5999. Min Act: -0.1700

Data Index: 7800284 (Open Web Text)

Max Activating Token Index: 619

Text #13

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.5429. Min Act: -0.1700

Data Index: 1826794 (Open Web Text)

Max Activating Token Index: 959

Text #14

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.5815. Min Act: -0.1700

Data Index: 4708050 (Open Web Text)

Max Activating Token Index: 856

Text #15

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.5965. Min Act: -0.1700

Data Index: 4932106 (Open Web Text)

Max Activating Token Index: 63

Text #16

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.6218. Min Act: -0.1700

Data Index: 6039550 (Open Web Text)

Max Activating Token Index: 411

Text #17

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.5606. Min Act: -0.1700

Data Index: 4140733 (Open Web Text)

Max Activating Token Index: 352

Text #18

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.5637. Min Act: -0.1700

Data Index: 7155827 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.9933. Min Range: -3.9933

Max Act: 3.6377. Min Act: -0.1700

Data Index: 2217914 (Open Web Text)

Max Activating Token Index: 775