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

Dataset: Open Web Text

Neuron 656 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: 4.7035. Min Range: -4.7035

Max Act: 4.7035. Min Act: -0.1700

Data Index: 1278881 (Open Web Text)

Max Activating Token Index: 893

Text #1

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6509. Min Act: -0.1700

Data Index: 590228 (Open Web Text)

Max Activating Token Index: 467

Text #2

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6749. Min Act: -0.1700

Data Index: 3574826 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6569. Min Act: -0.1700

Data Index: 5527330 (Open Web Text)

Max Activating Token Index: 764

Text #4

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6755. Min Act: -0.1700

Data Index: 4148280 (Open Web Text)

Max Activating Token Index: 240

Text #5

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6527. Min Act: -0.1700

Data Index: 8766945 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6877. Min Act: -0.1700

Data Index: 2055328 (Open Web Text)

Max Activating Token Index: 782

Text #7

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6431. Min Act: -0.1700

Data Index: 8243782 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6195. Min Act: -0.1700

Data Index: 6131305 (Open Web Text)

Max Activating Token Index: 904

Text #9

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6160. Min Act: -0.1700

Data Index: 2926914 (Open Web Text)

Max Activating Token Index: 376

Text #10

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6252. Min Act: -0.1700

Data Index: 8464880 (Open Web Text)

Max Activating Token Index: 201

Text #11

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6017. Min Act: -0.1700

Data Index: 654084 (Open Web Text)

Max Activating Token Index: 321

Text #12

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6485. Min Act: -0.1700

Data Index: 1571652 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6195. Min Act: -0.1700

Data Index: 1387861 (Open Web Text)

Max Activating Token Index: 599

Text #14

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6291. Min Act: -0.1700

Data Index: 7680879 (Open Web Text)

Max Activating Token Index: 705

Text #15

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6074. Min Act: -0.1700

Data Index: 7200729 (Open Web Text)

Max Activating Token Index: 235

Text #16

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6115. Min Act: -0.1700

Data Index: 1025119 (Open Web Text)

Max Activating Token Index: 257

Text #17

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6198. Min Act: -0.1700

Data Index: 7158603 (Open Web Text)

Max Activating Token Index: 833

Text #18

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6282. Min Act: -0.1700

Data Index: 696784 (Open Web Text)

Max Activating Token Index: 924

Text #19

Max Range: 4.7035. Min Range: -4.7035

Max Act: 4.6119. Min Act: -0.1700

Data Index: 4677453 (Open Web Text)

Max Activating Token Index: 825