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

Dataset: Open Web Text

Neuron 1375 in Layer 1

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: 1.7922. Min Range: -1.7922

Max Act: 1.7922. Min Act: -0.1699

Data Index: 5276401 (Open Web Text)

Max Activating Token Index: 150

Text #1

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.7549. Min Act: -0.1700

Data Index: 5815248 (Open Web Text)

Max Activating Token Index: 283

Text #2

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.7480. Min Act: -0.1700

Data Index: 5962623 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.7189. Min Act: -0.1700

Data Index: 4532810 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.7227. Min Act: -0.1700

Data Index: 406426 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.7175. Min Act: -0.1700

Data Index: 7571654 (Open Web Text)

Max Activating Token Index: 368

Text #6

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6953. Min Act: -0.1700

Data Index: 8156838 (Open Web Text)

Max Activating Token Index: 651

Text #7

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6965. Min Act: -0.1700

Data Index: 7465902 (Open Web Text)

Max Activating Token Index: 482

Text #8

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6914. Min Act: -0.1700

Data Index: 7558180 (Open Web Text)

Max Activating Token Index: 125

Text #9

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6975. Min Act: -0.1687

Data Index: 530486 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6933. Min Act: -0.1700

Data Index: 3908964 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6858. Min Act: -0.1700

Data Index: 7978462 (Open Web Text)

Max Activating Token Index: 381

Text #12

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6755. Min Act: -0.1700

Data Index: 8428820 (Open Web Text)

Max Activating Token Index: 526

Text #13

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6691. Min Act: -0.1700

Data Index: 5921236 (Open Web Text)

Max Activating Token Index: 72

Text #14

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6718. Min Act: -0.1697

Data Index: 1903307 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6706. Min Act: -0.1700

Data Index: 8221647 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6767. Min Act: -0.1700

Data Index: 1577024 (Open Web Text)

Max Activating Token Index: 202

Text #17

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6714. Min Act: -0.1700

Data Index: 7758672 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6685. Min Act: -0.1700

Data Index: 7030539 (Open Web Text)

Max Activating Token Index: 295

Text #19

Max Range: 1.7922. Min Range: -1.7922

Max Act: 1.6637. Min Act: -0.1700

Data Index: 8070606 (Open Web Text)

Max Activating Token Index: 724