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

Dataset: Open Web Text

Neuron 3006 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: 3.8055. Min Range: -3.8055

Max Act: 3.8055. Min Act: -0.1700

Data Index: 6083634 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.7099. Min Act: -0.1700

Data Index: 8779651 (Open Web Text)

Max Activating Token Index: 352

Text #2

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.6953. Min Act: -0.1700

Data Index: 7291342 (Open Web Text)

Max Activating Token Index: 494

Text #3

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.5546. Min Act: -0.1700

Data Index: 4031766 (Open Web Text)

Max Activating Token Index: 337

Text #4

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4868. Min Act: -0.1700

Data Index: 3372782 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4807. Min Act: -0.1700

Data Index: 5546205 (Open Web Text)

Max Activating Token Index: 915

Text #6

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4736. Min Act: -0.1700

Data Index: 1943642 (Open Web Text)

Max Activating Token Index: 1017

Text #7

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4567. Min Act: -0.1700

Data Index: 3205826 (Open Web Text)

Max Activating Token Index: 280

Text #8

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4761. Min Act: -0.1700

Data Index: 532856 (Open Web Text)

Max Activating Token Index: 250

Text #9

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4644. Min Act: -0.1700

Data Index: 7310444 (Open Web Text)

Max Activating Token Index: 180

Text #10

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4359. Min Act: -0.1700

Data Index: 1723121 (Open Web Text)

Max Activating Token Index: 295

Text #11

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4420. Min Act: -0.1700

Data Index: 5821660 (Open Web Text)

Max Activating Token Index: 837

Text #12

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4483. Min Act: -0.1700

Data Index: 1523616 (Open Web Text)

Max Activating Token Index: 784

Text #13

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4093. Min Act: -0.1700

Data Index: 4460267 (Open Web Text)

Max Activating Token Index: 214

Text #14

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.3542. Min Act: -0.1700

Data Index: 67206 (Open Web Text)

Max Activating Token Index: 809

Text #15

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.3902. Min Act: -0.1700

Data Index: 6326421 (Open Web Text)

Max Activating Token Index: 545

Text #16

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.3664. Min Act: -0.1700

Data Index: 3188421 (Open Web Text)

Max Activating Token Index: 553

Text #17

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4145. Min Act: -0.1700

Data Index: 2081266 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.4126. Min Act: -0.1700

Data Index: 7634594 (Open Web Text)

Max Activating Token Index: 181

Text #19

Max Range: 3.8055. Min Range: -3.8055

Max Act: 3.3845. Min Act: -0.1700

Data Index: 6289208 (Open Web Text)

Max Activating Token Index: 303