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

Dataset: Open Web Text

Neuron 1283 in Layer 0

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: 0.8298. Min Range: -0.8298

Max Act: 0.8298. Min Act: -0.1700

Data Index: 2177509 (Open Web Text)

Max Activating Token Index: 214

Text #1

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.8093. Min Act: -0.1700

Data Index: 5673721 (Open Web Text)

Max Activating Token Index: 724

Text #2

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.8087. Min Act: -0.1700

Data Index: 3619355 (Open Web Text)

Max Activating Token Index: 929

Text #3

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.8061. Min Act: -0.1700

Data Index: 5673722 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.8040. Min Act: -0.1700

Data Index: 5328944 (Open Web Text)

Max Activating Token Index: 215

Text #5

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7977. Min Act: -0.1700

Data Index: 2606307 (Open Web Text)

Max Activating Token Index: 224

Text #6

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7908. Min Act: -0.1700

Data Index: 2841151 (Open Web Text)

Max Activating Token Index: 923

Text #7

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7961. Min Act: -0.1700

Data Index: 5377507 (Open Web Text)

Max Activating Token Index: 229

Text #8

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7894. Min Act: -0.1700

Data Index: 6505124 (Open Web Text)

Max Activating Token Index: 920

Text #9

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7848. Min Act: -0.1699

Data Index: 8229979 (Open Web Text)

Max Activating Token Index: 207

Text #10

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7852. Min Act: -0.1699

Data Index: 4704606 (Open Web Text)

Max Activating Token Index: 351

Text #11

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7718. Min Act: -0.1700

Data Index: 3158126 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7746. Min Act: -0.1700

Data Index: 5503927 (Open Web Text)

Max Activating Token Index: 754

Text #13

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7641. Min Act: -0.1700

Data Index: 2742894 (Open Web Text)

Max Activating Token Index: 210

Text #14

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7676. Min Act: -0.1700

Data Index: 5059827 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7713. Min Act: -0.1700

Data Index: 8182741 (Open Web Text)

Max Activating Token Index: 927

Text #16

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7673. Min Act: -0.1699

Data Index: 4197105 (Open Web Text)

Max Activating Token Index: 225

Text #17

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7747. Min Act: -0.1700

Data Index: 5503956 (Open Web Text)

Max Activating Token Index: 711

Text #18

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7713. Min Act: -0.1700

Data Index: 2595698 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7604. Min Act: -0.1700

Data Index: 2265420 (Open Web Text)

Max Activating Token Index: 924