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

Dataset: Open Web Text

Neuron 2723 in Layer 3

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: 4.7914. Min Range: -4.7914

Max Act: 4.7914. Min Act: -0.1698

Data Index: 6817211 (Open Web Text)

Max Activating Token Index: 332

Text #1

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.4171. Min Act: -0.1694

Data Index: 6104408 (Open Web Text)

Max Activating Token Index: 389

Text #2

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.3579. Min Act: -0.1700

Data Index: 4987842 (Open Web Text)

Max Activating Token Index: 515

Text #3

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.3475. Min Act: -0.1694

Data Index: 6551148 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.3949. Min Act: -0.1700

Data Index: 6117651 (Open Web Text)

Max Activating Token Index: 26

Text #5

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.0305. Min Act: -0.1700

Data Index: 83169 (Open Web Text)

Max Activating Token Index: 543

Text #6

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.1443. Min Act: -0.1700

Data Index: 4412275 (Open Web Text)

Max Activating Token Index: 478

Text #7

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.1284. Min Act: -0.1700

Data Index: 2433813 (Open Web Text)

Max Activating Token Index: 476

Text #8

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.1523. Min Act: -0.1700

Data Index: 6146510 (Open Web Text)

Max Activating Token Index: 400

Text #9

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.1903. Min Act: -0.1700

Data Index: 1619884 (Open Web Text)

Max Activating Token Index: 129

Text #10

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.1409. Min Act: -0.1700

Data Index: 8691751 (Open Web Text)

Max Activating Token Index: 933

Text #11

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.0593. Min Act: -0.1700

Data Index: 670976 (Open Web Text)

Max Activating Token Index: 275

Text #12

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.2194. Min Act: -0.1700

Data Index: 4420097 (Open Web Text)

Max Activating Token Index: 636

Text #13

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.0282. Min Act: -0.1700

Data Index: 484030 (Open Web Text)

Max Activating Token Index: 651

Text #14

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.0632. Min Act: -0.1700

Data Index: 5454146 (Open Web Text)

Max Activating Token Index: 618

Text #15

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.1259. Min Act: -0.1700

Data Index: 3594292 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.0381. Min Act: -0.1696

Data Index: 4800046 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.1610. Min Act: -0.1700

Data Index: 6403689 (Open Web Text)

Max Activating Token Index: 937

Text #18

Max Range: 4.7914. Min Range: -4.7914

Max Act: 4.1088. Min Act: -0.1700

Data Index: 2919856 (Open Web Text)

Max Activating Token Index: 144

Text #19

Max Range: 4.7914. Min Range: -4.7914

Max Act: 3.9975. Min Act: -0.1700

Data Index: 5571073 (Open Web Text)

Max Activating Token Index: 411