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

Dataset: Open Web Text

Neuron 1901 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: 3.1318. Min Range: -3.1318

Max Act: 3.1318. Min Act: -0.1700

Data Index: 6902864 (Open Web Text)

Max Activating Token Index: 188

Text #1

Max Range: 3.1318. Min Range: -3.1318

Max Act: 3.1270. Min Act: -0.1700

Data Index: 3277642 (Open Web Text)

Max Activating Token Index: 756

Text #2

Max Range: 3.1318. Min Range: -3.1318

Max Act: 3.0743. Min Act: -0.1700

Data Index: 968992 (Open Web Text)

Max Activating Token Index: 614

Text #3

Max Range: 3.1318. Min Range: -3.1318

Max Act: 3.0641. Min Act: -0.1700

Data Index: 8545356 (Open Web Text)

Max Activating Token Index: 310

Text #4

Max Range: 3.1318. Min Range: -3.1318

Max Act: 3.0723. Min Act: -0.1700

Data Index: 4581097 (Open Web Text)

Max Activating Token Index: 821

Text #5

Max Range: 3.1318. Min Range: -3.1318

Max Act: 3.0457. Min Act: -0.1700

Data Index: 7223172 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 3.1318. Min Range: -3.1318

Max Act: 3.0264. Min Act: -0.1700

Data Index: 5105130 (Open Web Text)

Max Activating Token Index: 119

Text #7

Max Range: 3.1318. Min Range: -3.1318

Max Act: 3.0149. Min Act: -0.1700

Data Index: 1129218 (Open Web Text)

Max Activating Token Index: 577

Text #8

Max Range: 3.1318. Min Range: -3.1318

Max Act: 3.0012. Min Act: -0.1700

Data Index: 5822156 (Open Web Text)

Max Activating Token Index: 694

Text #9

Max Range: 3.1318. Min Range: -3.1318

Max Act: 3.0073. Min Act: -0.1700

Data Index: 5156439 (Open Web Text)

Max Activating Token Index: 360

Text #10

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.9749. Min Act: -0.1700

Data Index: 3785748 (Open Web Text)

Max Activating Token Index: 666

Text #11

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.9650. Min Act: -0.1700

Data Index: 3253470 (Open Web Text)

Max Activating Token Index: 466

Text #12

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.9573. Min Act: -0.1700

Data Index: 2485439 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.9463. Min Act: -0.1700

Data Index: 1266660 (Open Web Text)

Max Activating Token Index: 201

Text #14

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.9303. Min Act: -0.1700

Data Index: 5772191 (Open Web Text)

Max Activating Token Index: 891

Text #15

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.9208. Min Act: -0.1700

Data Index: 94995 (Open Web Text)

Max Activating Token Index: 641

Text #16

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.9017. Min Act: -0.1700

Data Index: 3749177 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.9007. Min Act: -0.1700

Data Index: 3838558 (Open Web Text)

Max Activating Token Index: 246

Text #18

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.9004. Min Act: -0.1700

Data Index: 8222462 (Open Web Text)

Max Activating Token Index: 231

Text #19

Max Range: 3.1318. Min Range: -3.1318

Max Act: 2.9078. Min Act: -0.1700

Data Index: 8222463 (Open Web Text)

Max Activating Token Index: 22