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

Dataset: Open Web Text

Neuron 257 in Layer 6

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: 3.9522. Min Range: -3.9522

Max Act: 3.9522. Min Act: -0.1700

Data Index: 1327070 (Open Web Text)

Max Activating Token Index: 813

Text #1

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.8591. Min Act: -0.1700

Data Index: 1458226 (Open Web Text)

Max Activating Token Index: 973

Text #2

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.8448. Min Act: -0.1700

Data Index: 2909237 (Open Web Text)

Max Activating Token Index: 892

Text #3

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.8366. Min Act: -0.1700

Data Index: 5742235 (Open Web Text)

Max Activating Token Index: 600

Text #4

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.8318. Min Act: -0.1700

Data Index: 7195063 (Open Web Text)

Max Activating Token Index: 1010

Text #5

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.8416. Min Act: -0.1700

Data Index: 4962055 (Open Web Text)

Max Activating Token Index: 997

Text #6

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.8434. Min Act: -0.1700

Data Index: 6007786 (Open Web Text)

Max Activating Token Index: 734

Text #7

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.8618. Min Act: -0.1700

Data Index: 8255495 (Open Web Text)

Max Activating Token Index: 820

Text #8

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7952. Min Act: -0.1700

Data Index: 165934 (Open Web Text)

Max Activating Token Index: 818

Text #9

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7658. Min Act: -0.1700

Data Index: 4665733 (Open Web Text)

Max Activating Token Index: 865

Text #10

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7717. Min Act: -0.1700

Data Index: 2909236 (Open Web Text)

Max Activating Token Index: 894

Text #11

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7617. Min Act: -0.1700

Data Index: 5169881 (Open Web Text)

Max Activating Token Index: 990

Text #12

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7551. Min Act: -0.1700

Data Index: 8234916 (Open Web Text)

Max Activating Token Index: 724

Text #13

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7939. Min Act: -0.1700

Data Index: 4957177 (Open Web Text)

Max Activating Token Index: 819

Text #14

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7384. Min Act: -0.1700

Data Index: 2824752 (Open Web Text)

Max Activating Token Index: 547

Text #15

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7402. Min Act: -0.1700

Data Index: 3112560 (Open Web Text)

Max Activating Token Index: 747

Text #16

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7395. Min Act: -0.1700

Data Index: 6007785 (Open Web Text)

Max Activating Token Index: 803

Text #17

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7093. Min Act: -0.1700

Data Index: 1205129 (Open Web Text)

Max Activating Token Index: 735

Text #18

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.7311. Min Act: -0.1700

Data Index: 4473824 (Open Web Text)

Max Activating Token Index: 695

Text #19

Max Range: 3.9522. Min Range: -3.9522

Max Act: 3.6600. Min Act: -0.1700

Data Index: 2267651 (Open Web Text)

Max Activating Token Index: 1023