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

Dataset: Open Web Text

Neuron 1254 in Layer 2

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: 4.1203. Min Range: -4.1203

Max Act: 4.1203. Min Act: -0.1700

Data Index: 8550814 (Open Web Text)

Max Activating Token Index: 81

Text #1

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.1035. Min Act: -0.1700

Data Index: 2270775 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0570. Min Act: -0.1700

Data Index: 5682591 (Open Web Text)

Max Activating Token Index: 715

Text #3

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0531. Min Act: -0.1700

Data Index: 7074728 (Open Web Text)

Max Activating Token Index: 226

Text #4

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0351. Min Act: -0.1700

Data Index: 5345640 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0373. Min Act: -0.1700

Data Index: 1267238 (Open Web Text)

Max Activating Token Index: 760

Text #6

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0375. Min Act: -0.1700

Data Index: 27580 (Open Web Text)

Max Activating Token Index: 95

Text #7

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0407. Min Act: -0.1700

Data Index: 7967480 (Open Web Text)

Max Activating Token Index: 596

Text #8

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0355. Min Act: -0.1699

Data Index: 8201453 (Open Web Text)

Max Activating Token Index: 353

Text #9

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0106. Min Act: -0.1700

Data Index: 4017409 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0133. Min Act: -0.1700

Data Index: 4929053 (Open Web Text)

Max Activating Token Index: 584

Text #11

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0247. Min Act: -0.1700

Data Index: 2633119 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 4.1203. Min Range: -4.1203

Max Act: 4.0206. Min Act: -0.1700

Data Index: 2532278 (Open Web Text)

Max Activating Token Index: 730

Text #13

Max Range: 4.1203. Min Range: -4.1203

Max Act: 3.9993. Min Act: -0.1700

Data Index: 324577 (Open Web Text)

Max Activating Token Index: 173

Text #14

Max Range: 4.1203. Min Range: -4.1203

Max Act: 3.9658. Min Act: -0.1700

Data Index: 1996986 (Open Web Text)

Max Activating Token Index: 51

Text #15

Max Range: 4.1203. Min Range: -4.1203

Max Act: 3.9826. Min Act: -0.1700

Data Index: 2676368 (Open Web Text)

Max Activating Token Index: 997

Text #16

Max Range: 4.1203. Min Range: -4.1203

Max Act: 3.9824. Min Act: -0.1700

Data Index: 1438342 (Open Web Text)

Max Activating Token Index: 785

Text #17

Max Range: 4.1203. Min Range: -4.1203

Max Act: 3.9620. Min Act: -0.1700

Data Index: 3007185 (Open Web Text)

Max Activating Token Index: 653

Text #18

Max Range: 4.1203. Min Range: -4.1203

Max Act: 3.9591. Min Act: -0.1700

Data Index: 3925907 (Open Web Text)

Max Activating Token Index: 40

Text #19

Max Range: 4.1203. Min Range: -4.1203

Max Act: 3.9765. Min Act: -0.1700

Data Index: 2239688 (Open Web Text)

Max Activating Token Index: 233