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

Dataset: Open Web Text

Neuron 2645 in Layer 5

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: 3.0250. Min Range: -3.0250

Max Act: 3.0250. Min Act: -0.1700

Data Index: 1542688 (Open Web Text)

Max Activating Token Index: 224

Text #1

Max Range: 3.0250. Min Range: -3.0250

Max Act: 3.0155. Min Act: -0.1700

Data Index: 2795003 (Open Web Text)

Max Activating Token Index: 412

Text #2

Max Range: 3.0250. Min Range: -3.0250

Max Act: 3.0007. Min Act: -0.1700

Data Index: 1147576 (Open Web Text)

Max Activating Token Index: 393

Text #3

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9796. Min Act: -0.1700

Data Index: 8164910 (Open Web Text)

Max Activating Token Index: 342

Text #4

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9600. Min Act: -0.1700

Data Index: 3634832 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9805. Min Act: -0.1700

Data Index: 8441926 (Open Web Text)

Max Activating Token Index: 769

Text #6

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9465. Min Act: -0.1700

Data Index: 1881621 (Open Web Text)

Max Activating Token Index: 209

Text #7

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9382. Min Act: -0.1700

Data Index: 3755783 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9545. Min Act: -0.1700

Data Index: 6928833 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9231. Min Act: -0.1700

Data Index: 3352278 (Open Web Text)

Max Activating Token Index: 881

Text #10

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9269. Min Act: -0.1700

Data Index: 1479864 (Open Web Text)

Max Activating Token Index: 56

Text #11

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9141. Min Act: -0.1700

Data Index: 8176980 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9133. Min Act: -0.1700

Data Index: 3506839 (Open Web Text)

Max Activating Token Index: 258

Text #13

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9297. Min Act: -0.1700

Data Index: 3838154 (Open Web Text)

Max Activating Token Index: 912

Text #14

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9246. Min Act: -0.1700

Data Index: 3790639 (Open Web Text)

Max Activating Token Index: 940

Text #15

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9201. Min Act: -0.1700

Data Index: 7212944 (Open Web Text)

Max Activating Token Index: 111

Text #16

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9224. Min Act: -0.1700

Data Index: 3224681 (Open Web Text)

Max Activating Token Index: 474

Text #17

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9218. Min Act: -0.1700

Data Index: 4721280 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.9146. Min Act: -0.1700

Data Index: 3101416 (Open Web Text)

Max Activating Token Index: 937

Text #19

Max Range: 3.0250. Min Range: -3.0250

Max Act: 2.8919. Min Act: -0.1700

Data Index: 3938149 (Open Web Text)

Max Activating Token Index: 343