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

Dataset: Open Web Text

Neuron 2739 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: 3.1514. Min Range: -3.1514

Max Act: 3.1493. Min Act: -0.1700

Data Index: 5077393 (Open Web Text)

Max Activating Token Index: 417

Text #1

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.1336. Min Act: -0.1700

Data Index: 1897064 (Open Web Text)

Max Activating Token Index: 476

Text #2

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.1514. Min Act: -0.1700

Data Index: 6535616 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.1084. Min Act: -0.1700

Data Index: 639034 (Open Web Text)

Max Activating Token Index: 142

Text #4

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.1064. Min Act: -0.1700

Data Index: 3270997 (Open Web Text)

Max Activating Token Index: 730

Text #5

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.1211. Min Act: -0.1700

Data Index: 2582581 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.1295. Min Act: -0.1700

Data Index: 5284921 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.1092. Min Act: -0.1700

Data Index: 6535613 (Open Web Text)

Max Activating Token Index: 680

Text #8

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.0927. Min Act: -0.1700

Data Index: 8286684 (Open Web Text)

Max Activating Token Index: 708

Text #9

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.1010. Min Act: -0.1700

Data Index: 2383109 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.1354. Min Act: -0.1700

Data Index: 418173 (Open Web Text)

Max Activating Token Index: 586

Text #11

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.0932. Min Act: -0.1700

Data Index: 6982701 (Open Web Text)

Max Activating Token Index: 204

Text #12

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.0668. Min Act: -0.1700

Data Index: 4426216 (Open Web Text)

Max Activating Token Index: 443

Text #13

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.0662. Min Act: -0.1700

Data Index: 867771 (Open Web Text)

Max Activating Token Index: 307

Text #14

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.0622. Min Act: -0.1700

Data Index: 3966823 (Open Web Text)

Max Activating Token Index: 105

Text #15

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.0878. Min Act: -0.1700

Data Index: 4420930 (Open Web Text)

Max Activating Token Index: 493

Text #16

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.0558. Min Act: -0.1700

Data Index: 8686117 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.0308. Min Act: -0.1700

Data Index: 3031024 (Open Web Text)

Max Activating Token Index: 108

Text #18

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.0593. Min Act: -0.1700

Data Index: 2931682 (Open Web Text)

Max Activating Token Index: 241

Text #19

Max Range: 3.1514. Min Range: -3.1514

Max Act: 3.0417. Min Act: -0.1700

Data Index: 8431792 (Open Web Text)

Max Activating Token Index: 225