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

Dataset: Open Web Text

Neuron 953 in Layer 6

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: 3.5018. Min Range: -3.5018

Max Act: 3.5018. Min Act: -0.1700

Data Index: 5700743 (Open Web Text)

Max Activating Token Index: 439

Text #1

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.4711. Min Act: -0.1700

Data Index: 3083178 (Open Web Text)

Max Activating Token Index: 884

Text #2

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.4780. Min Act: -0.1700

Data Index: 2350726 (Open Web Text)

Max Activating Token Index: 738

Text #3

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.4077. Min Act: -0.1700

Data Index: 3807763 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.4347. Min Act: -0.1700

Data Index: 6443397 (Open Web Text)

Max Activating Token Index: 300

Text #5

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.4458. Min Act: -0.1700

Data Index: 7202069 (Open Web Text)

Max Activating Token Index: 359

Text #6

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.4251. Min Act: -0.1700

Data Index: 3706624 (Open Web Text)

Max Activating Token Index: 315

Text #7

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3972. Min Act: -0.1700

Data Index: 136338 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3818. Min Act: -0.1700

Data Index: 7483174 (Open Web Text)

Max Activating Token Index: 311

Text #9

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3716. Min Act: -0.1700

Data Index: 784704 (Open Web Text)

Max Activating Token Index: 143

Text #10

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3416. Min Act: -0.1700

Data Index: 6820415 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3753. Min Act: -0.1700

Data Index: 2950078 (Open Web Text)

Max Activating Token Index: 332

Text #12

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3626. Min Act: -0.1700

Data Index: 8440604 (Open Web Text)

Max Activating Token Index: 971

Text #13

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3488. Min Act: -0.1700

Data Index: 1378362 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3383. Min Act: -0.1700

Data Index: 2203184 (Open Web Text)

Max Activating Token Index: 172

Text #15

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3431. Min Act: -0.1700

Data Index: 4494872 (Open Web Text)

Max Activating Token Index: 503

Text #16

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3127. Min Act: -0.1700

Data Index: 2253950 (Open Web Text)

Max Activating Token Index: 519

Text #17

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.2999. Min Act: -0.1700

Data Index: 794707 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3128. Min Act: -0.1700

Data Index: 2553390 (Open Web Text)

Max Activating Token Index: 964

Text #19

Max Range: 3.5018. Min Range: -3.5018

Max Act: 3.3175. Min Act: -0.1700

Data Index: 5700742 (Open Web Text)

Max Activating Token Index: 953