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

Dataset: Open Web Text

Neuron 2802 in Layer 5

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: 3.2436. Min Range: -3.2436

Max Act: 3.2436. Min Act: -0.1700

Data Index: 39127 (Open Web Text)

Max Activating Token Index: 725

Text #1

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.2003. Min Act: -0.1700

Data Index: 896602 (Open Web Text)

Max Activating Token Index: 65

Text #2

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.1715. Min Act: -0.1700

Data Index: 6197788 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.1526. Min Act: -0.1700

Data Index: 6316868 (Open Web Text)

Max Activating Token Index: 687

Text #4

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.1377. Min Act: -0.1700

Data Index: 5881437 (Open Web Text)

Max Activating Token Index: 475

Text #5

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.1009. Min Act: -0.1700

Data Index: 2101908 (Open Web Text)

Max Activating Token Index: 119

Text #6

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0836. Min Act: -0.1700

Data Index: 6331233 (Open Web Text)

Max Activating Token Index: 736

Text #7

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0779. Min Act: -0.1700

Data Index: 3081303 (Open Web Text)

Max Activating Token Index: 151

Text #8

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0814. Min Act: -0.1700

Data Index: 3096868 (Open Web Text)

Max Activating Token Index: 105

Text #9

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0730. Min Act: -0.1700

Data Index: 4247625 (Open Web Text)

Max Activating Token Index: 150

Text #10

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0924. Min Act: -0.1700

Data Index: 7905223 (Open Web Text)

Max Activating Token Index: 856

Text #11

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0686. Min Act: -0.1700

Data Index: 7856269 (Open Web Text)

Max Activating Token Index: 812

Text #12

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0404. Min Act: -0.1700

Data Index: 8045625 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0732. Min Act: -0.1700

Data Index: 7525336 (Open Web Text)

Max Activating Token Index: 654

Text #14

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0592. Min Act: -0.1700

Data Index: 7370922 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0514. Min Act: -0.1700

Data Index: 825138 (Open Web Text)

Max Activating Token Index: 603

Text #16

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0471. Min Act: -0.1700

Data Index: 5811629 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0217. Min Act: -0.1700

Data Index: 2486583 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0395. Min Act: -0.1700

Data Index: 7724606 (Open Web Text)

Max Activating Token Index: 801

Text #19

Max Range: 3.2436. Min Range: -3.2436

Max Act: 3.0206. Min Act: -0.1700

Data Index: 3066599 (Open Web Text)

Max Activating Token Index: 250