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

Dataset: Open Web Text

Neuron 836 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: 1.8209. Min Range: -1.8209

Max Act: 1.8209. Min Act: -0.1695

Data Index: 4517159 (Open Web Text)

Max Activating Token Index: 947

Text #1

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.8102. Min Act: -0.1699

Data Index: 631417 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.7819. Min Act: -0.1700

Data Index: 6529547 (Open Web Text)

Max Activating Token Index: 587

Text #3

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.7474. Min Act: -0.1676

Data Index: 696740 (Open Web Text)

Max Activating Token Index: 804

Text #4

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.7478. Min Act: -0.1700

Data Index: 6307292 (Open Web Text)

Max Activating Token Index: 880

Text #5

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.7281. Min Act: -0.1700

Data Index: 7625127 (Open Web Text)

Max Activating Token Index: 478

Text #6

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.7175. Min Act: -0.1700

Data Index: 540514 (Open Web Text)

Max Activating Token Index: 77

Text #7

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.7060. Min Act: -0.1700

Data Index: 3049587 (Open Web Text)

Max Activating Token Index: 598

Text #8

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6767. Min Act: -0.1700

Data Index: 5517210 (Open Web Text)

Max Activating Token Index: 556

Text #9

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6697. Min Act: -0.1700

Data Index: 4406852 (Open Web Text)

Max Activating Token Index: 217

Text #10

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6725. Min Act: -0.1700

Data Index: 1712602 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6708. Min Act: -0.1700

Data Index: 1317333 (Open Web Text)

Max Activating Token Index: 133

Text #12

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6761. Min Act: -0.1700

Data Index: 3529171 (Open Web Text)

Max Activating Token Index: 733

Text #13

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6696. Min Act: -0.1700

Data Index: 7635343 (Open Web Text)

Max Activating Token Index: 419

Text #14

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6610. Min Act: -0.1700

Data Index: 5030196 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6594. Min Act: -0.1700

Data Index: 8519563 (Open Web Text)

Max Activating Token Index: 961

Text #16

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6591. Min Act: -0.1700

Data Index: 3599446 (Open Web Text)

Max Activating Token Index: 662

Text #17

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6576. Min Act: -0.1700

Data Index: 2280681 (Open Web Text)

Max Activating Token Index: 673

Text #18

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6492. Min Act: -0.1700

Data Index: 4062389 (Open Web Text)

Max Activating Token Index: 146

Text #19

Max Range: 1.8209. Min Range: -1.8209

Max Act: 1.6470. Min Act: -0.1700

Data Index: 2244619 (Open Web Text)

Max Activating Token Index: 338