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

Dataset: Open Web Text

Neuron 1652 in Layer 4

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: 5.1497. Min Range: -5.1497

Max Act: 5.1497. Min Act: -0.1700

Data Index: 5070778 (Open Web Text)

Max Activating Token Index: 48

Text #1

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.9139. Min Act: -0.1700

Data Index: 3744025 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.9033. Min Act: -0.1700

Data Index: 3780065 (Open Web Text)

Max Activating Token Index: 226

Text #3

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.8527. Min Act: -0.1700

Data Index: 6031133 (Open Web Text)

Max Activating Token Index: 67

Text #4

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7565. Min Act: -0.1700

Data Index: 8504796 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.8342. Min Act: -0.1700

Data Index: 1415891 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7873. Min Act: -0.1700

Data Index: 6029181 (Open Web Text)

Max Activating Token Index: 237

Text #7

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7900. Min Act: -0.1700

Data Index: 3145283 (Open Web Text)

Max Activating Token Index: 182

Text #8

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7804. Min Act: -0.1700

Data Index: 3008914 (Open Web Text)

Max Activating Token Index: 236

Text #9

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7451. Min Act: -0.1700

Data Index: 4644266 (Open Web Text)

Max Activating Token Index: 105

Text #10

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7326. Min Act: -0.1700

Data Index: 5551952 (Open Web Text)

Max Activating Token Index: 186

Text #11

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7566. Min Act: -0.1700

Data Index: 6091710 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7781. Min Act: -0.1700

Data Index: 2147264 (Open Web Text)

Max Activating Token Index: 884

Text #13

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7849. Min Act: -0.1700

Data Index: 6680055 (Open Web Text)

Max Activating Token Index: 855

Text #14

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7611. Min Act: -0.1700

Data Index: 2927308 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7901. Min Act: -0.1700

Data Index: 934924 (Open Web Text)

Max Activating Token Index: 34

Text #16

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.6924. Min Act: -0.1700

Data Index: 8734174 (Open Web Text)

Max Activating Token Index: 285

Text #17

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7590. Min Act: -0.1700

Data Index: 7662180 (Open Web Text)

Max Activating Token Index: 624

Text #18

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7618. Min Act: -0.1700

Data Index: 3708469 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 5.1497. Min Range: -5.1497

Max Act: 4.7073. Min Act: -0.1700

Data Index: 4432553 (Open Web Text)

Max Activating Token Index: 418