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

Dataset: Open Web Text

Neuron 2015 in Layer 4

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: 3.6573. Min Range: -3.6573

Max Act: 3.6573. Min Act: -0.1700

Data Index: 5609571 (Open Web Text)

Max Activating Token Index: 501

Text #1

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.5747. Min Act: -0.1700

Data Index: 4961174 (Open Web Text)

Max Activating Token Index: 621

Text #2

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.5378. Min Act: -0.1700

Data Index: 8264503 (Open Web Text)

Max Activating Token Index: 671

Text #3

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.5161. Min Act: -0.1700

Data Index: 4070258 (Open Web Text)

Max Activating Token Index: 129

Text #4

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4857. Min Act: -0.1700

Data Index: 2187321 (Open Web Text)

Max Activating Token Index: 454

Text #5

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4912. Min Act: -0.1700

Data Index: 1049633 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4996. Min Act: -0.1700

Data Index: 4309111 (Open Web Text)

Max Activating Token Index: 745

Text #7

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4961. Min Act: -0.1700

Data Index: 4880769 (Open Web Text)

Max Activating Token Index: 806

Text #8

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4682. Min Act: -0.1700

Data Index: 4919444 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4594. Min Act: -0.1700

Data Index: 309116 (Open Web Text)

Max Activating Token Index: 653

Text #10

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4618. Min Act: -0.1700

Data Index: 4002225 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4381. Min Act: -0.1700

Data Index: 4265225 (Open Web Text)

Max Activating Token Index: 185

Text #12

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4475. Min Act: -0.1700

Data Index: 1715402 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4602. Min Act: -0.1700

Data Index: 5576542 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4469. Min Act: -0.1700

Data Index: 3229412 (Open Web Text)

Max Activating Token Index: 726

Text #15

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4458. Min Act: -0.1700

Data Index: 8784654 (Open Web Text)

Max Activating Token Index: 808

Text #16

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4661. Min Act: -0.1700

Data Index: 861419 (Open Web Text)

Max Activating Token Index: 850

Text #17

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4283. Min Act: -0.1700

Data Index: 1073340 (Open Web Text)

Max Activating Token Index: 685

Text #18

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4087. Min Act: -0.1700

Data Index: 2736137 (Open Web Text)

Max Activating Token Index: 436

Text #19

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4089. Min Act: -0.1700

Data Index: 8379608 (Open Web Text)

Max Activating Token Index: 748