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

Dataset: Open Web Text

Neuron 2474 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: 1.8483. Min Range: -1.8483

Max Act: 1.8483. Min Act: -0.1700

Data Index: 241706 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7827. Min Act: -0.1700

Data Index: 4150106 (Open Web Text)

Max Activating Token Index: 638

Text #2

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7639. Min Act: -0.1700

Data Index: 922705 (Open Web Text)

Max Activating Token Index: 214

Text #3

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7221. Min Act: -0.1700

Data Index: 2916211 (Open Web Text)

Max Activating Token Index: 394

Text #4

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7024. Min Act: -0.1700

Data Index: 3058119 (Open Web Text)

Max Activating Token Index: 621

Text #5

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7115. Min Act: -0.1700

Data Index: 4208671 (Open Web Text)

Max Activating Token Index: 780

Text #6

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7010. Min Act: -0.1700

Data Index: 8046968 (Open Web Text)

Max Activating Token Index: 813

Text #7

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7268. Min Act: -0.1700

Data Index: 4412955 (Open Web Text)

Max Activating Token Index: 528

Text #8

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7137. Min Act: -0.1700

Data Index: 7180913 (Open Web Text)

Max Activating Token Index: 1019

Text #9

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7047. Min Act: -0.1700

Data Index: 4710027 (Open Web Text)

Max Activating Token Index: 468

Text #10

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6961. Min Act: -0.1700

Data Index: 2603733 (Open Web Text)

Max Activating Token Index: 295

Text #11

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7092. Min Act: -0.1700

Data Index: 5021505 (Open Web Text)

Max Activating Token Index: 956

Text #12

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6887. Min Act: -0.1700

Data Index: 3163981 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6781. Min Act: -0.1700

Data Index: 1141389 (Open Web Text)

Max Activating Token Index: 680

Text #14

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6966. Min Act: -0.1700

Data Index: 6744536 (Open Web Text)

Max Activating Token Index: 921

Text #15

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.7022. Min Act: -0.1700

Data Index: 7751231 (Open Web Text)

Max Activating Token Index: 620

Text #16

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6910. Min Act: -0.1700

Data Index: 8481671 (Open Web Text)

Max Activating Token Index: 789

Text #17

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6800. Min Act: -0.1700

Data Index: 2057941 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6822. Min Act: -0.1700

Data Index: 5232398 (Open Web Text)

Max Activating Token Index: 691

Text #19

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6766. Min Act: -0.1700

Data Index: 5821326 (Open Web Text)

Max Activating Token Index: 833