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

Dataset: Open Web Text

Neuron 2095 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: 3.2076. Min Range: -3.2076

Max Act: 3.2076. Min Act: -0.1700

Data Index: 4278903 (Open Web Text)

Max Activating Token Index: 425

Text #1

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.1893. Min Act: -0.1700

Data Index: 1924554 (Open Web Text)

Max Activating Token Index: 594

Text #2

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.1131. Min Act: -0.1700

Data Index: 8527450 (Open Web Text)

Max Activating Token Index: 595

Text #3

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.0655. Min Act: -0.1700

Data Index: 8446796 (Open Web Text)

Max Activating Token Index: 281

Text #4

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.0575. Min Act: -0.1700

Data Index: 8688051 (Open Web Text)

Max Activating Token Index: 73

Text #5

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.0203. Min Act: -0.1700

Data Index: 5170923 (Open Web Text)

Max Activating Token Index: 513

Text #6

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.0442. Min Act: -0.1700

Data Index: 6893327 (Open Web Text)

Max Activating Token Index: 776

Text #7

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.0438. Min Act: -0.1700

Data Index: 5461720 (Open Web Text)

Max Activating Token Index: 402

Text #8

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.0446. Min Act: -0.1700

Data Index: 487747 (Open Web Text)

Max Activating Token Index: 160

Text #9

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.0443. Min Act: -0.1700

Data Index: 8816225 (Open Web Text)

Max Activating Token Index: 546

Text #10

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.0247. Min Act: -0.1700

Data Index: 2593343 (Open Web Text)

Max Activating Token Index: 135

Text #11

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.0323. Min Act: -0.1700

Data Index: 7773612 (Open Web Text)

Max Activating Token Index: 645

Text #12

Max Range: 3.2076. Min Range: -3.2076

Max Act: 2.9693. Min Act: -0.1700

Data Index: 7708201 (Open Web Text)

Max Activating Token Index: 931

Text #13

Max Range: 3.2076. Min Range: -3.2076

Max Act: 3.0300. Min Act: -0.1700

Data Index: 4712763 (Open Web Text)

Max Activating Token Index: 689

Text #14

Max Range: 3.2076. Min Range: -3.2076

Max Act: 2.9907. Min Act: -0.1700

Data Index: 3909181 (Open Web Text)

Max Activating Token Index: 273

Text #15

Max Range: 3.2076. Min Range: -3.2076

Max Act: 2.9709. Min Act: -0.1700

Data Index: 3771326 (Open Web Text)

Max Activating Token Index: 317

Text #16

Max Range: 3.2076. Min Range: -3.2076

Max Act: 2.9804. Min Act: -0.1700

Data Index: 6324826 (Open Web Text)

Max Activating Token Index: 831

Text #17

Max Range: 3.2076. Min Range: -3.2076

Max Act: 2.9678. Min Act: -0.1700

Data Index: 4893178 (Open Web Text)

Max Activating Token Index: 170

Text #18

Max Range: 3.2076. Min Range: -3.2076

Max Act: 2.9580. Min Act: -0.1700

Data Index: 4456572 (Open Web Text)

Max Activating Token Index: 696

Text #19

Max Range: 3.2076. Min Range: -3.2076

Max Act: 2.9253. Min Act: -0.1700

Data Index: 7240613 (Open Web Text)

Max Activating Token Index: 450