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

Dataset: Open Web Text

Neuron 940 in Layer 2

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: 1.2896. Min Range: -1.2896

Max Act: 1.2896. Min Act: -0.1700

Data Index: 7278953 (Open Web Text)

Max Activating Token Index: 32

Text #1

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2449. Min Act: -0.1451

Data Index: 7447018 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2263. Min Act: -0.1698

Data Index: 8809332 (Open Web Text)

Max Activating Token Index: 391

Text #3

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2291. Min Act: -0.1700

Data Index: 4039693 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2334. Min Act: -0.1700

Data Index: 88241 (Open Web Text)

Max Activating Token Index: 270

Text #5

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2224. Min Act: -0.1700

Data Index: 1713325 (Open Web Text)

Max Activating Token Index: 173

Text #6

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2095. Min Act: -0.1700

Data Index: 2153044 (Open Web Text)

Max Activating Token Index: 345

Text #7

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2142. Min Act: -0.1700

Data Index: 1287123 (Open Web Text)

Max Activating Token Index: 394

Text #8

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2098. Min Act: -0.1698

Data Index: 3494094 (Open Web Text)

Max Activating Token Index: 481

Text #9

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1936. Min Act: -0.1681

Data Index: 5554290 (Open Web Text)

Max Activating Token Index: 363

Text #10

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.2036. Min Act: -0.1700

Data Index: 5040701 (Open Web Text)

Max Activating Token Index: 665

Text #11

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1997. Min Act: -0.1700

Data Index: 4055263 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1888. Min Act: -0.1700

Data Index: 7447021 (Open Web Text)

Max Activating Token Index: 744

Text #13

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1853. Min Act: -0.1700

Data Index: 5869011 (Open Web Text)

Max Activating Token Index: 48

Text #14

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1946. Min Act: -0.1700

Data Index: 3638003 (Open Web Text)

Max Activating Token Index: 117

Text #15

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1984. Min Act: -0.1694

Data Index: 8235138 (Open Web Text)

Max Activating Token Index: 244

Text #16

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1851. Min Act: -0.1700

Data Index: 7247758 (Open Web Text)

Max Activating Token Index: 308

Text #17

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1940. Min Act: -0.1664

Data Index: 3020005 (Open Web Text)

Max Activating Token Index: 84

Text #18

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1801. Min Act: -0.1699

Data Index: 4364311 (Open Web Text)

Max Activating Token Index: 184

Text #19

Max Range: 1.2896. Min Range: -1.2896

Max Act: 1.1769. Min Act: -0.1700

Data Index: 1125254 (Open Web Text)

Max Activating Token Index: 550