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

Dataset: Open Web Text

Neuron 1185 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: 4.8506. Min Range: -4.8506

Max Act: 4.8148. Min Act: -0.1700

Data Index: 3354700 (Open Web Text)

Max Activating Token Index: 130

Text #1

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.8506. Min Act: -0.1700

Data Index: 1155691 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.7538. Min Act: -0.1700

Data Index: 2431942 (Open Web Text)

Max Activating Token Index: 82

Text #3

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.6875. Min Act: -0.1700

Data Index: 3699630 (Open Web Text)

Max Activating Token Index: 157

Text #4

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.5179. Min Act: -0.1700

Data Index: 4861017 (Open Web Text)

Max Activating Token Index: 986

Text #5

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.4674. Min Act: -0.1700

Data Index: 4191834 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.4873. Min Act: -0.1700

Data Index: 1155692 (Open Web Text)

Max Activating Token Index: 84

Text #7

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.3822. Min Act: -0.1700

Data Index: 3445310 (Open Web Text)

Max Activating Token Index: 703

Text #8

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.3422. Min Act: -0.1700

Data Index: 229777 (Open Web Text)

Max Activating Token Index: 458

Text #9

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.3466. Min Act: -0.1700

Data Index: 4111376 (Open Web Text)

Max Activating Token Index: 76

Text #10

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.3006. Min Act: -0.1700

Data Index: 6521762 (Open Web Text)

Max Activating Token Index: 270

Text #11

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.3284. Min Act: -0.1700

Data Index: 5508879 (Open Web Text)

Max Activating Token Index: 930

Text #12

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.3040. Min Act: -0.1700

Data Index: 8320836 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.3166. Min Act: -0.1700

Data Index: 2653008 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.3285. Min Act: -0.1700

Data Index: 1478921 (Open Web Text)

Max Activating Token Index: 831

Text #15

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.2780. Min Act: -0.1700

Data Index: 1679153 (Open Web Text)

Max Activating Token Index: 885

Text #16

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.2821. Min Act: -0.1700

Data Index: 3307862 (Open Web Text)

Max Activating Token Index: 513

Text #17

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.2771. Min Act: -0.1700

Data Index: 3618626 (Open Web Text)

Max Activating Token Index: 814

Text #18

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.2661. Min Act: -0.1700

Data Index: 2965960 (Open Web Text)

Max Activating Token Index: 161

Text #19

Max Range: 4.8506. Min Range: -4.8506

Max Act: 4.2776. Min Act: -0.1700

Data Index: 1408336 (Open Web Text)

Max Activating Token Index: 609