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

Dataset: Open Web Text

Neuron 1303 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: 7.1337. Min Range: -7.1337

Max Act: 7.1337. Min Act: -0.1700

Data Index: 2224539 (Open Web Text)

Max Activating Token Index: 910

Text #1

Max Range: 7.1337. Min Range: -7.1337

Max Act: 6.8809. Min Act: -0.1700

Data Index: 8597733 (Open Web Text)

Max Activating Token Index: 890

Text #2

Max Range: 7.1337. Min Range: -7.1337

Max Act: 6.5120. Min Act: -0.1700

Data Index: 6149037 (Open Web Text)

Max Activating Token Index: 926

Text #3

Max Range: 7.1337. Min Range: -7.1337

Max Act: 6.3335. Min Act: -0.1700

Data Index: 4925823 (Open Web Text)

Max Activating Token Index: 904

Text #4

Max Range: 7.1337. Min Range: -7.1337

Max Act: 6.0079. Min Act: -0.1700

Data Index: 7711028 (Open Web Text)

Max Activating Token Index: 900

Text #5

Max Range: 7.1337. Min Range: -7.1337

Max Act: 5.9011. Min Act: -0.1700

Data Index: 544228 (Open Web Text)

Max Activating Token Index: 907

Text #6

Max Range: 7.1337. Min Range: -7.1337

Max Act: 6.0208. Min Act: -0.1700

Data Index: 2664195 (Open Web Text)

Max Activating Token Index: 888

Text #7

Max Range: 7.1337. Min Range: -7.1337

Max Act: 5.6717. Min Act: -0.1700

Data Index: 3670547 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 7.1337. Min Range: -7.1337

Max Act: 5.4935. Min Act: -0.1700

Data Index: 6397931 (Open Web Text)

Max Activating Token Index: 881

Text #9

Max Range: 7.1337. Min Range: -7.1337

Max Act: 5.3337. Min Act: -0.1700

Data Index: 4430766 (Open Web Text)

Max Activating Token Index: 896

Text #10

Max Range: 7.1337. Min Range: -7.1337

Max Act: 5.2758. Min Act: -0.1700

Data Index: 1084800 (Open Web Text)

Max Activating Token Index: 975

Text #11

Max Range: 7.1337. Min Range: -7.1337

Max Act: 5.1420. Min Act: -0.1700

Data Index: 5620017 (Open Web Text)

Max Activating Token Index: 902

Text #12

Max Range: 7.1337. Min Range: -7.1337

Max Act: 5.0745. Min Act: -0.1700

Data Index: 3824737 (Open Web Text)

Max Activating Token Index: 830

Text #13

Max Range: 7.1337. Min Range: -7.1337

Max Act: 5.1402. Min Act: -0.1700

Data Index: 2259150 (Open Web Text)

Max Activating Token Index: 888

Text #14

Max Range: 7.1337. Min Range: -7.1337

Max Act: 4.8866. Min Act: -0.1700

Data Index: 4431419 (Open Web Text)

Max Activating Token Index: 997

Text #15

Max Range: 7.1337. Min Range: -7.1337

Max Act: 4.9268. Min Act: -0.1700

Data Index: 8461265 (Open Web Text)

Max Activating Token Index: 933

Text #16

Max Range: 7.1337. Min Range: -7.1337

Max Act: 4.5358. Min Act: -0.1700

Data Index: 1666408 (Open Web Text)

Max Activating Token Index: 612

Text #17

Max Range: 7.1337. Min Range: -7.1337

Max Act: 4.6617. Min Act: -0.1700

Data Index: 4271295 (Open Web Text)

Max Activating Token Index: 926

Text #18

Max Range: 7.1337. Min Range: -7.1337

Max Act: 4.4160. Min Act: -0.1700

Data Index: 5057707 (Open Web Text)

Max Activating Token Index: 898

Text #19

Max Range: 7.1337. Min Range: -7.1337

Max Act: 4.2801. Min Act: -0.1700

Data Index: 7473794 (Open Web Text)

Max Activating Token Index: 892