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

Dataset: Open Web Text

Neuron 761 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: 4.7515. Min Range: -4.7515

Max Act: 4.7515. Min Act: -0.1700

Data Index: 1567686 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6825. Min Act: -0.1700

Data Index: 55226 (Open Web Text)

Max Activating Token Index: 683

Text #2

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6951. Min Act: -0.1700

Data Index: 4322044 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.7103. Min Act: -0.1700

Data Index: 3100056 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.7212. Min Act: -0.1700

Data Index: 1380050 (Open Web Text)

Max Activating Token Index: 987

Text #5

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6468. Min Act: -0.1700

Data Index: 7255582 (Open Web Text)

Max Activating Token Index: 132

Text #6

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6737. Min Act: -0.1700

Data Index: 3219357 (Open Web Text)

Max Activating Token Index: 563

Text #7

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6420. Min Act: -0.1700

Data Index: 8815298 (Open Web Text)

Max Activating Token Index: 675

Text #8

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6675. Min Act: -0.1700

Data Index: 3568566 (Open Web Text)

Max Activating Token Index: 322

Text #9

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6601. Min Act: -0.1700

Data Index: 4610547 (Open Web Text)

Max Activating Token Index: 950

Text #10

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6496. Min Act: -0.1700

Data Index: 2878974 (Open Web Text)

Max Activating Token Index: 810

Text #11

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6615. Min Act: -0.1700

Data Index: 4087116 (Open Web Text)

Max Activating Token Index: 484

Text #12

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6684. Min Act: -0.1700

Data Index: 2579622 (Open Web Text)

Max Activating Token Index: 773

Text #13

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6077. Min Act: -0.1700

Data Index: 2241844 (Open Web Text)

Max Activating Token Index: 777

Text #14

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6319. Min Act: -0.1700

Data Index: 2472146 (Open Web Text)

Max Activating Token Index: 936

Text #15

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6483. Min Act: -0.1700

Data Index: 5422939 (Open Web Text)

Max Activating Token Index: 869

Text #16

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6352. Min Act: -0.1700

Data Index: 5917272 (Open Web Text)

Max Activating Token Index: 517

Text #17

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6155. Min Act: -0.1700

Data Index: 4721395 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.5902. Min Act: -0.1700

Data Index: 913698 (Open Web Text)

Max Activating Token Index: 257

Text #19

Max Range: 4.7515. Min Range: -4.7515

Max Act: 4.6121. Min Act: -0.1700

Data Index: 4809067 (Open Web Text)

Max Activating Token Index: 960