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

Dataset: Open Web Text

Neuron 2549 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: 3.5565. Min Range: -3.5565

Max Act: 3.5391. Min Act: -0.1700

Data Index: 2696601 (Open Web Text)

Max Activating Token Index: 40

Text #1

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.5565. Min Act: -0.1700

Data Index: 6243128 (Open Web Text)

Max Activating Token Index: 843

Text #2

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.5175. Min Act: -0.1700

Data Index: 6639952 (Open Web Text)

Max Activating Token Index: 422

Text #3

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.4913. Min Act: -0.1700

Data Index: 748524 (Open Web Text)

Max Activating Token Index: 644

Text #4

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.4617. Min Act: -0.1700

Data Index: 4112630 (Open Web Text)

Max Activating Token Index: 1000

Text #5

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.4389. Min Act: -0.1700

Data Index: 3683066 (Open Web Text)

Max Activating Token Index: 59

Text #6

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.4138. Min Act: -0.1700

Data Index: 4079194 (Open Web Text)

Max Activating Token Index: 730

Text #7

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.4209. Min Act: -0.1700

Data Index: 8785115 (Open Web Text)

Max Activating Token Index: 760

Text #8

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.3872. Min Act: -0.1700

Data Index: 2415800 (Open Web Text)

Max Activating Token Index: 381

Text #9

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.4100. Min Act: -0.1700

Data Index: 3367807 (Open Web Text)

Max Activating Token Index: 873

Text #10

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.4106. Min Act: -0.1700

Data Index: 534131 (Open Web Text)

Max Activating Token Index: 857

Text #11

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.4065. Min Act: -0.1700

Data Index: 8773380 (Open Web Text)

Max Activating Token Index: 146

Text #12

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.3905. Min Act: -0.1700

Data Index: 2635935 (Open Web Text)

Max Activating Token Index: 268

Text #13

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.4032. Min Act: -0.1700

Data Index: 7692568 (Open Web Text)

Max Activating Token Index: 193

Text #14

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.3806. Min Act: -0.1700

Data Index: 3419904 (Open Web Text)

Max Activating Token Index: 363

Text #15

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.4205. Min Act: -0.1700

Data Index: 1981807 (Open Web Text)

Max Activating Token Index: 691

Text #16

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.3699. Min Act: -0.1700

Data Index: 1617910 (Open Web Text)

Max Activating Token Index: 699

Text #17

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.3718. Min Act: -0.1700

Data Index: 6370079 (Open Web Text)

Max Activating Token Index: 648

Text #18

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.3645. Min Act: -0.1700

Data Index: 2463027 (Open Web Text)

Max Activating Token Index: 738

Text #19

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.3483. Min Act: -0.1700

Data Index: 3117229 (Open Web Text)

Max Activating Token Index: 409