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

Dataset: Open Web Text

Neuron 1712 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: 3.9364. Min Range: -3.9364

Max Act: 3.9364. Min Act: -0.1700

Data Index: 1394868 (Open Web Text)

Max Activating Token Index: 337

Text #1

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.9102. Min Act: -0.1700

Data Index: 5300149 (Open Web Text)

Max Activating Token Index: 588

Text #2

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.8929. Min Act: -0.1700

Data Index: 3349657 (Open Web Text)

Max Activating Token Index: 874

Text #3

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.8321. Min Act: -0.1700

Data Index: 3038395 (Open Web Text)

Max Activating Token Index: 259

Text #4

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.8184. Min Act: -0.1700

Data Index: 5373199 (Open Web Text)

Max Activating Token Index: 412

Text #5

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.8020. Min Act: -0.1700

Data Index: 5169839 (Open Web Text)

Max Activating Token Index: 912

Text #6

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.8212. Min Act: -0.1700

Data Index: 1637778 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7912. Min Act: -0.1700

Data Index: 6758448 (Open Web Text)

Max Activating Token Index: 745

Text #8

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7748. Min Act: -0.1700

Data Index: 4733792 (Open Web Text)

Max Activating Token Index: 586

Text #9

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7762. Min Act: -0.1700

Data Index: 766920 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7462. Min Act: -0.1700

Data Index: 766926 (Open Web Text)

Max Activating Token Index: 721

Text #11

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7776. Min Act: -0.1700

Data Index: 7176708 (Open Web Text)

Max Activating Token Index: 338

Text #12

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7907. Min Act: -0.1700

Data Index: 2123269 (Open Web Text)

Max Activating Token Index: 386

Text #13

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7748. Min Act: -0.1700

Data Index: 5407441 (Open Web Text)

Max Activating Token Index: 959

Text #14

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7760. Min Act: -0.1700

Data Index: 3349658 (Open Web Text)

Max Activating Token Index: 382

Text #15

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7726. Min Act: -0.1700

Data Index: 6758447 (Open Web Text)

Max Activating Token Index: 592

Text #16

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7499. Min Act: -0.1700

Data Index: 6616807 (Open Web Text)

Max Activating Token Index: 886

Text #17

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7860. Min Act: -0.1700

Data Index: 3096987 (Open Web Text)

Max Activating Token Index: 307

Text #18

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7550. Min Act: -0.1700

Data Index: 1127171 (Open Web Text)

Max Activating Token Index: 934

Text #19

Max Range: 3.9364. Min Range: -3.9364

Max Act: 3.7545. Min Act: -0.1700

Data Index: 294176 (Open Web Text)

Max Activating Token Index: 1023