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

Dataset: Open Web Text

Neuron 1972 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: 3.4748. Min Range: -3.4748

Max Act: 3.4748. Min Act: -0.1700

Data Index: 7292853 (Open Web Text)

Max Activating Token Index: 663

Text #1

Max Range: 3.4748. Min Range: -3.4748

Max Act: 3.3056. Min Act: -0.1700

Data Index: 3731530 (Open Web Text)

Max Activating Token Index: 126

Text #2

Max Range: 3.4748. Min Range: -3.4748

Max Act: 3.2076. Min Act: -0.1700

Data Index: 7774885 (Open Web Text)

Max Activating Token Index: 510

Text #3

Max Range: 3.4748. Min Range: -3.4748

Max Act: 3.1119. Min Act: -0.1700

Data Index: 6345657 (Open Web Text)

Max Activating Token Index: 50

Text #4

Max Range: 3.4748. Min Range: -3.4748

Max Act: 3.1053. Min Act: -0.1700

Data Index: 7211702 (Open Web Text)

Max Activating Token Index: 879

Text #5

Max Range: 3.4748. Min Range: -3.4748

Max Act: 3.0602. Min Act: -0.1700

Data Index: 2523536 (Open Web Text)

Max Activating Token Index: 919

Text #6

Max Range: 3.4748. Min Range: -3.4748

Max Act: 3.0002. Min Act: -0.1700

Data Index: 7051893 (Open Web Text)

Max Activating Token Index: 635

Text #7

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.9653. Min Act: -0.1700

Data Index: 1030569 (Open Web Text)

Max Activating Token Index: 444

Text #8

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.9570. Min Act: -0.1700

Data Index: 3109492 (Open Web Text)

Max Activating Token Index: 44

Text #9

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.9337. Min Act: -0.1700

Data Index: 2865401 (Open Web Text)

Max Activating Token Index: 815

Text #10

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.9410. Min Act: -0.1700

Data Index: 2441169 (Open Web Text)

Max Activating Token Index: 121

Text #11

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.9433. Min Act: -0.1700

Data Index: 5592827 (Open Web Text)

Max Activating Token Index: 770

Text #12

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.9191. Min Act: -0.1700

Data Index: 7547160 (Open Web Text)

Max Activating Token Index: 383

Text #13

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.9284. Min Act: -0.1700

Data Index: 4281994 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.9145. Min Act: -0.1700

Data Index: 3399352 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.9243. Min Act: -0.1700

Data Index: 518318 (Open Web Text)

Max Activating Token Index: 549

Text #16

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.8954. Min Act: -0.1700

Data Index: 8538611 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.9329. Min Act: -0.1700

Data Index: 3124611 (Open Web Text)

Max Activating Token Index: 911

Text #18

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.8888. Min Act: -0.1700

Data Index: 7197051 (Open Web Text)

Max Activating Token Index: 781

Text #19

Max Range: 3.4748. Min Range: -3.4748

Max Act: 2.8898. Min Act: -0.1700

Data Index: 2324217 (Open Web Text)

Max Activating Token Index: 320