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

Dataset: Open Web Text

Neuron 2992 in Layer 0

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: 0.8340. Min Range: -0.8340

Max Act: 0.8340. Min Act: -0.1700

Data Index: 5092549 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.8301. Min Act: -0.1700

Data Index: 5149180 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.8188. Min Act: -0.1700

Data Index: 383070 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.8266. Min Act: -0.1700

Data Index: 5989853 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.8224. Min Act: -0.1700

Data Index: 883217 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.8070. Min Act: -0.1699

Data Index: 5442883 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7985. Min Act: -0.1700

Data Index: 3658263 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7937. Min Act: -0.1700

Data Index: 3792422 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7869. Min Act: -0.1700

Data Index: 5609352 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7844. Min Act: -0.1700

Data Index: 1576914 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7780. Min Act: -0.1700

Data Index: 8734160 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7776. Min Act: -0.1700

Data Index: 5432032 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7787. Min Act: -0.1700

Data Index: 448923 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7819. Min Act: -0.1700

Data Index: 4668384 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7758. Min Act: -0.1700

Data Index: 1679558 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7778. Min Act: -0.1700

Data Index: 8448686 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7765. Min Act: -0.1700

Data Index: 7141593 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7783. Min Act: -0.1700

Data Index: 2345661 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7719. Min Act: -0.1700

Data Index: 7814697 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7768. Min Act: -0.1700

Data Index: 3693319 (Open Web Text)

Max Activating Token Index: 15