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

Dataset: Open Web Text

Neuron 1775 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: 3.3505. Min Range: -3.3505

Max Act: 3.3501. Min Act: -0.1700

Data Index: 8140446 (Open Web Text)

Max Activating Token Index: 638

Text #1

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.3505. Min Act: -0.1700

Data Index: 2159928 (Open Web Text)

Max Activating Token Index: 444

Text #2

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.3086. Min Act: -0.1700

Data Index: 8827330 (Open Web Text)

Max Activating Token Index: 280

Text #3

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.2927. Min Act: -0.1700

Data Index: 7171461 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.2625. Min Act: -0.1700

Data Index: 615087 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.2307. Min Act: -0.1700

Data Index: 884228 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.2167. Min Act: -0.1700

Data Index: 5177761 (Open Web Text)

Max Activating Token Index: 494

Text #7

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.2117. Min Act: -0.1700

Data Index: 7020484 (Open Web Text)

Max Activating Token Index: 22

Text #8

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.2033. Min Act: -0.1700

Data Index: 5338342 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1933. Min Act: -0.1700

Data Index: 8179594 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1722. Min Act: -0.1700

Data Index: 7478612 (Open Web Text)

Max Activating Token Index: 907

Text #11

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1625. Min Act: -0.1700

Data Index: 3270865 (Open Web Text)

Max Activating Token Index: 960

Text #12

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1663. Min Act: -0.1700

Data Index: 416131 (Open Web Text)

Max Activating Token Index: 866

Text #13

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1562. Min Act: -0.1700

Data Index: 3112995 (Open Web Text)

Max Activating Token Index: 598

Text #14

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1605. Min Act: -0.1700

Data Index: 2035118 (Open Web Text)

Max Activating Token Index: 178

Text #15

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1461. Min Act: -0.1700

Data Index: 6279367 (Open Web Text)

Max Activating Token Index: 905

Text #16

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1444. Min Act: -0.1700

Data Index: 891041 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1433. Min Act: -0.1700

Data Index: 1083498 (Open Web Text)

Max Activating Token Index: 166

Text #18

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1284. Min Act: -0.1700

Data Index: 4362350 (Open Web Text)

Max Activating Token Index: 393

Text #19

Max Range: 3.3505. Min Range: -3.3505

Max Act: 3.1213. Min Act: -0.1700

Data Index: 4591481 (Open Web Text)

Max Activating Token Index: 326