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

Dataset: Open Web Text

Neuron 2186 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: 3.2542. Min Range: -3.2542

Max Act: 3.2474. Min Act: -0.1700

Data Index: 5637345 (Open Web Text)

Max Activating Token Index: 985

Text #1

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.2542. Min Act: -0.1700

Data Index: 3964025 (Open Web Text)

Max Activating Token Index: 389

Text #2

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.1859. Min Act: -0.1700

Data Index: 5518424 (Open Web Text)

Max Activating Token Index: 482

Text #3

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.1370. Min Act: -0.1700

Data Index: 3226533 (Open Web Text)

Max Activating Token Index: 973

Text #4

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.1152. Min Act: -0.1700

Data Index: 1655008 (Open Web Text)

Max Activating Token Index: 919

Text #5

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0895. Min Act: -0.1700

Data Index: 3674496 (Open Web Text)

Max Activating Token Index: 992

Text #6

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0971. Min Act: -0.1700

Data Index: 1979987 (Open Web Text)

Max Activating Token Index: 379

Text #7

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0652. Min Act: -0.1700

Data Index: 6333216 (Open Web Text)

Max Activating Token Index: 470

Text #8

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0657. Min Act: -0.1700

Data Index: 6183169 (Open Web Text)

Max Activating Token Index: 286

Text #9

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0430. Min Act: -0.1700

Data Index: 3161074 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0587. Min Act: -0.1700

Data Index: 7189515 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0468. Min Act: -0.1700

Data Index: 6185198 (Open Web Text)

Max Activating Token Index: 93

Text #12

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0545. Min Act: -0.1700

Data Index: 1768948 (Open Web Text)

Max Activating Token Index: 833

Text #13

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0110. Min Act: -0.1700

Data Index: 3196818 (Open Web Text)

Max Activating Token Index: 427

Text #14

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0182. Min Act: -0.1700

Data Index: 1050358 (Open Web Text)

Max Activating Token Index: 368

Text #15

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0241. Min Act: -0.1700

Data Index: 3284214 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0298. Min Act: -0.1700

Data Index: 7607134 (Open Web Text)

Max Activating Token Index: 790

Text #17

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0252. Min Act: -0.1700

Data Index: 2204770 (Open Web Text)

Max Activating Token Index: 615

Text #18

Max Range: 3.2542. Min Range: -3.2542

Max Act: 2.9945. Min Act: -0.1700

Data Index: 406245 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 3.2542. Min Range: -3.2542

Max Act: 3.0249. Min Act: -0.1700

Data Index: 1104108 (Open Web Text)

Max Activating Token Index: 974