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

Dataset: Open Web Text

Neuron 1478 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: 3.0316. Min Range: -3.0316

Max Act: 3.0316. Min Act: -0.1700

Data Index: 8571432 (Open Web Text)

Max Activating Token Index: 79

Text #1

Max Range: 3.0316. Min Range: -3.0316

Max Act: 3.0003. Min Act: -0.1700

Data Index: 361285 (Open Web Text)

Max Activating Token Index: 887

Text #2

Max Range: 3.0316. Min Range: -3.0316

Max Act: 3.0014. Min Act: -0.1700

Data Index: 5590883 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9792. Min Act: -0.1700

Data Index: 6646623 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9546. Min Act: -0.1700

Data Index: 3295504 (Open Web Text)

Max Activating Token Index: 685

Text #5

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9519. Min Act: -0.1700

Data Index: 5588802 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9584. Min Act: -0.1700

Data Index: 3011597 (Open Web Text)

Max Activating Token Index: 620

Text #7

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9573. Min Act: -0.1700

Data Index: 4321996 (Open Web Text)

Max Activating Token Index: 502

Text #8

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9630. Min Act: -0.1700

Data Index: 7604504 (Open Web Text)

Max Activating Token Index: 687

Text #9

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9548. Min Act: -0.1700

Data Index: 3846492 (Open Web Text)

Max Activating Token Index: 793

Text #10

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9383. Min Act: -0.1700

Data Index: 8769017 (Open Web Text)

Max Activating Token Index: 214

Text #11

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9268. Min Act: -0.1700

Data Index: 3348921 (Open Web Text)

Max Activating Token Index: 859

Text #12

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9400. Min Act: -0.1700

Data Index: 3054991 (Open Web Text)

Max Activating Token Index: 581

Text #13

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9497. Min Act: -0.1700

Data Index: 3529814 (Open Web Text)

Max Activating Token Index: 918

Text #14

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9397. Min Act: -0.1700

Data Index: 1465888 (Open Web Text)

Max Activating Token Index: 730

Text #15

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9142. Min Act: -0.1700

Data Index: 7927584 (Open Web Text)

Max Activating Token Index: 949

Text #16

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9356. Min Act: -0.1700

Data Index: 4099083 (Open Web Text)

Max Activating Token Index: 414

Text #17

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9287. Min Act: -0.1700

Data Index: 6250692 (Open Web Text)

Max Activating Token Index: 465

Text #18

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9455. Min Act: -0.1700

Data Index: 6108513 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 3.0316. Min Range: -3.0316

Max Act: 2.9180. Min Act: -0.1700

Data Index: 4544115 (Open Web Text)

Max Activating Token Index: 847