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

Dataset: Open Web Text

Neuron 516 in Layer 1

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: 1.8468. Min Range: -1.8468

Max Act: 1.8468. Min Act: -0.1700

Data Index: 4165382 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.8246. Min Act: -0.1700

Data Index: 8216806 (Open Web Text)

Max Activating Token Index: 826

Text #2

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.8197. Min Act: -0.1700

Data Index: 3208119 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.8060. Min Act: -0.1700

Data Index: 4504421 (Open Web Text)

Max Activating Token Index: 35

Text #4

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.8210. Min Act: -0.1700

Data Index: 28392 (Open Web Text)

Max Activating Token Index: 448

Text #5

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.8113. Min Act: -0.1700

Data Index: 8437022 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7975. Min Act: -0.1700

Data Index: 6836322 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7976. Min Act: -0.1700

Data Index: 4881059 (Open Web Text)

Max Activating Token Index: 754

Text #8

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7931. Min Act: -0.1700

Data Index: 5666741 (Open Web Text)

Max Activating Token Index: 349

Text #9

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7922. Min Act: -0.1700

Data Index: 8639990 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7819. Min Act: -0.1700

Data Index: 34941 (Open Web Text)

Max Activating Token Index: 991

Text #11

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7892. Min Act: -0.1700

Data Index: 2672468 (Open Web Text)

Max Activating Token Index: 772

Text #12

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7785. Min Act: -0.1700

Data Index: 1002046 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7789. Min Act: -0.1700

Data Index: 5989412 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7702. Min Act: -0.1700

Data Index: 8773731 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7661. Min Act: -0.1700

Data Index: 7317553 (Open Web Text)

Max Activating Token Index: 402

Text #16

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7714. Min Act: -0.1700

Data Index: 7427797 (Open Web Text)

Max Activating Token Index: 151

Text #17

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7691. Min Act: -0.1700

Data Index: 6193977 (Open Web Text)

Max Activating Token Index: 433

Text #18

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7652. Min Act: -0.1700

Data Index: 3208118 (Open Web Text)

Max Activating Token Index: 498

Text #19

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7647. Min Act: -0.1700

Data Index: 2184533 (Open Web Text)

Max Activating Token Index: 624