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

Dataset: Open Web Text

Neuron 1077 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: 3.5063. Min Range: -3.5063

Max Act: 3.5063. Min Act: -0.1700

Data Index: 5401563 (Open Web Text)

Max Activating Token Index: 306

Text #1

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.2304. Min Act: -0.1700

Data Index: 8556282 (Open Web Text)

Max Activating Token Index: 146

Text #2

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.2078. Min Act: -0.1700

Data Index: 4106727 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.2101. Min Act: -0.1700

Data Index: 4666199 (Open Web Text)

Max Activating Token Index: 517

Text #4

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.1735. Min Act: -0.1700

Data Index: 2540697 (Open Web Text)

Max Activating Token Index: 193

Text #5

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.1695. Min Act: -0.1700

Data Index: 1118400 (Open Web Text)

Max Activating Token Index: 666

Text #6

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.1677. Min Act: -0.1700

Data Index: 7924097 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.1770. Min Act: -0.1700

Data Index: 3503216 (Open Web Text)

Max Activating Token Index: 547

Text #8

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.1553. Min Act: -0.1700

Data Index: 1029638 (Open Web Text)

Max Activating Token Index: 141

Text #9

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.1582. Min Act: -0.1700

Data Index: 2116514 (Open Web Text)

Max Activating Token Index: 46

Text #10

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.1245. Min Act: -0.1700

Data Index: 6553230 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.1074. Min Act: -0.1700

Data Index: 7811405 (Open Web Text)

Max Activating Token Index: 995

Text #12

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.1178. Min Act: -0.1700

Data Index: 3898376 (Open Web Text)

Max Activating Token Index: 110

Text #13

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.0898. Min Act: -0.1700

Data Index: 3636438 (Open Web Text)

Max Activating Token Index: 631

Text #14

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.1197. Min Act: -0.1700

Data Index: 7711992 (Open Web Text)

Max Activating Token Index: 529

Text #15

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.0729. Min Act: -0.1700

Data Index: 8436581 (Open Web Text)

Max Activating Token Index: 480

Text #16

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.0916. Min Act: -0.1700

Data Index: 5995038 (Open Web Text)

Max Activating Token Index: 571

Text #17

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.0946. Min Act: -0.1700

Data Index: 1017630 (Open Web Text)

Max Activating Token Index: 301

Text #18

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.0734. Min Act: -0.1700

Data Index: 3440262 (Open Web Text)

Max Activating Token Index: 441

Text #19

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.0673. Min Act: -0.1700

Data Index: 6546091 (Open Web Text)

Max Activating Token Index: 8