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

Dataset: Open Web Text

Neuron 581 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: 4.2210. Min Range: -4.2210

Max Act: 4.2210. Min Act: -0.1700

Data Index: 5738400 (Open Web Text)

Max Activating Token Index: 550

Text #1

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.1070. Min Act: -0.1700

Data Index: 8137986 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.0661. Min Act: -0.1700

Data Index: 2744502 (Open Web Text)

Max Activating Token Index: 922

Text #3

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.1259. Min Act: -0.1696

Data Index: 4852697 (Open Web Text)

Max Activating Token Index: 82

Text #4

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.0362. Min Act: -0.1700

Data Index: 4415872 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.0156. Min Act: -0.1700

Data Index: 4738792 (Open Web Text)

Max Activating Token Index: 642

Text #6

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.0095. Min Act: -0.1700

Data Index: 4353108 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.0366. Min Act: -0.1700

Data Index: 7610476 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.0044. Min Act: -0.1696

Data Index: 7706749 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.0199. Min Act: -0.1700

Data Index: 1745729 (Open Web Text)

Max Activating Token Index: 883

Text #10

Max Range: 4.2210. Min Range: -4.2210

Max Act: 3.9628. Min Act: -0.1700

Data Index: 5477601 (Open Web Text)

Max Activating Token Index: 37

Text #11

Max Range: 4.2210. Min Range: -4.2210

Max Act: 3.9885. Min Act: -0.1700

Data Index: 5289220 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.0101. Min Act: -0.1700

Data Index: 4317518 (Open Web Text)

Max Activating Token Index: 629

Text #13

Max Range: 4.2210. Min Range: -4.2210

Max Act: 4.0209. Min Act: -0.1700

Data Index: 5757020 (Open Web Text)

Max Activating Token Index: 203

Text #14

Max Range: 4.2210. Min Range: -4.2210

Max Act: 3.9811. Min Act: -0.1700

Data Index: 7056851 (Open Web Text)

Max Activating Token Index: 174

Text #15

Max Range: 4.2210. Min Range: -4.2210

Max Act: 3.9773. Min Act: -0.1700

Data Index: 699957 (Open Web Text)

Max Activating Token Index: 513

Text #16

Max Range: 4.2210. Min Range: -4.2210

Max Act: 3.9977. Min Act: -0.1700

Data Index: 5668566 (Open Web Text)

Max Activating Token Index: 915

Text #17

Max Range: 4.2210. Min Range: -4.2210

Max Act: 3.9644. Min Act: -0.1700

Data Index: 6008027 (Open Web Text)

Max Activating Token Index: 222

Text #18

Max Range: 4.2210. Min Range: -4.2210

Max Act: 3.9122. Min Act: -0.1700

Data Index: 4564800 (Open Web Text)

Max Activating Token Index: 867

Text #19

Max Range: 4.2210. Min Range: -4.2210

Max Act: 3.8946. Min Act: -0.1699

Data Index: 2636241 (Open Web Text)

Max Activating Token Index: 430