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

Dataset: Open Web Text

Neuron 2303 in Layer 1

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: 2.0059. Min Range: -2.0059

Max Act: 2.0059. Min Act: -0.1700

Data Index: 8328925 (Open Web Text)

Max Activating Token Index: 189

Text #1

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.8629. Min Act: -0.1700

Data Index: 3438593 (Open Web Text)

Max Activating Token Index: 161

Text #2

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.8287. Min Act: -0.1700

Data Index: 6153052 (Open Web Text)

Max Activating Token Index: 165

Text #3

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.8229. Min Act: -0.1700

Data Index: 2512669 (Open Web Text)

Max Activating Token Index: 214

Text #4

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7685. Min Act: -0.1700

Data Index: 4529844 (Open Web Text)

Max Activating Token Index: 181

Text #5

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7677. Min Act: -0.1700

Data Index: 3296229 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7676. Min Act: -0.1700

Data Index: 2479006 (Open Web Text)

Max Activating Token Index: 181

Text #7

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7700. Min Act: -0.1700

Data Index: 2119775 (Open Web Text)

Max Activating Token Index: 196

Text #8

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7551. Min Act: -0.1700

Data Index: 4339528 (Open Web Text)

Max Activating Token Index: 183

Text #9

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7628. Min Act: -0.1700

Data Index: 7548753 (Open Web Text)

Max Activating Token Index: 180

Text #10

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7473. Min Act: -0.1700

Data Index: 5181326 (Open Web Text)

Max Activating Token Index: 201

Text #11

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7457. Min Act: -0.1700

Data Index: 5344496 (Open Web Text)

Max Activating Token Index: 162

Text #12

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7571. Min Act: -0.1700

Data Index: 8555181 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7357. Min Act: -0.1700

Data Index: 1044533 (Open Web Text)

Max Activating Token Index: 209

Text #14

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7342. Min Act: -0.1700

Data Index: 6109851 (Open Web Text)

Max Activating Token Index: 144

Text #15

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7328. Min Act: -0.1700

Data Index: 3529700 (Open Web Text)

Max Activating Token Index: 174

Text #16

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7309. Min Act: -0.1700

Data Index: 5804688 (Open Web Text)

Max Activating Token Index: 154

Text #17

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7439. Min Act: -0.1700

Data Index: 4488164 (Open Web Text)

Max Activating Token Index: 180

Text #18

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7330. Min Act: -0.1700

Data Index: 645153 (Open Web Text)

Max Activating Token Index: 167

Text #19

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.7330. Min Act: -0.1700

Data Index: 8382272 (Open Web Text)

Max Activating Token Index: 152