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

Dataset: Open Web Text

Neuron 1336 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: 4.2827. Min Range: -4.2827

Max Act: 4.2686. Min Act: -0.1700

Data Index: 5066534 (Open Web Text)

Max Activating Token Index: 599

Text #1

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.2767. Min Act: -0.1700

Data Index: 6464949 (Open Web Text)

Max Activating Token Index: 884

Text #2

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.2827. Min Act: -0.1700

Data Index: 7187548 (Open Web Text)

Max Activating Token Index: 152

Text #3

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.1921. Min Act: -0.1700

Data Index: 7445501 (Open Web Text)

Max Activating Token Index: 812

Text #4

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.2506. Min Act: -0.1700

Data Index: 1037531 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.1895. Min Act: -0.1700

Data Index: 940419 (Open Web Text)

Max Activating Token Index: 986

Text #6

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.1870. Min Act: -0.1700

Data Index: 7384023 (Open Web Text)

Max Activating Token Index: 1004

Text #7

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.1727. Min Act: -0.1700

Data Index: 982624 (Open Web Text)

Max Activating Token Index: 781

Text #8

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.1530. Min Act: -0.1700

Data Index: 5834325 (Open Web Text)

Max Activating Token Index: 237

Text #9

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.1005. Min Act: -0.1700

Data Index: 4601962 (Open Web Text)

Max Activating Token Index: 904

Text #10

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.0988. Min Act: -0.1700

Data Index: 1996419 (Open Web Text)

Max Activating Token Index: 143

Text #11

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.1177. Min Act: -0.1700

Data Index: 17174 (Open Web Text)

Max Activating Token Index: 440

Text #12

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.1492. Min Act: -0.1700

Data Index: 6705370 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.1240. Min Act: -0.1700

Data Index: 6871403 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.0678. Min Act: -0.1700

Data Index: 948851 (Open Web Text)

Max Activating Token Index: 885

Text #15

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.1097. Min Act: -0.1700

Data Index: 1574529 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.0939. Min Act: -0.1700

Data Index: 3062040 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.0648. Min Act: -0.1700

Data Index: 4912791 (Open Web Text)

Max Activating Token Index: 195

Text #18

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.0616. Min Act: -0.1700

Data Index: 239204 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 4.2827. Min Range: -4.2827

Max Act: 4.0923. Min Act: -0.1700

Data Index: 2411326 (Open Web Text)

Max Activating Token Index: 966