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

Dataset: Open Web Text

Neuron 1916 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: 5.0144. Min Range: -5.0144

Max Act: 5.0144. Min Act: -0.1700

Data Index: 2430547 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.9969. Min Act: -0.1700

Data Index: 7215750 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.9367. Min Act: -0.1700

Data Index: 577052 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.9203. Min Act: -0.1700

Data Index: 4370958 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8968. Min Act: -0.1700

Data Index: 5840893 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.9027. Min Act: -0.1700

Data Index: 3086202 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.9005. Min Act: -0.1700

Data Index: 8331113 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.9129. Min Act: -0.1700

Data Index: 6430440 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.9095. Min Act: -0.1700

Data Index: 5825112 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8681. Min Act: -0.1700

Data Index: 7095154 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8619. Min Act: -0.1700

Data Index: 2844432 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8869. Min Act: -0.1700

Data Index: 783920 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8637. Min Act: -0.1700

Data Index: 3494284 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8610. Min Act: -0.1700

Data Index: 2202647 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8525. Min Act: -0.1700

Data Index: 4733048 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8291. Min Act: -0.1700

Data Index: 4850438 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8469. Min Act: -0.1700

Data Index: 4991966 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8449. Min Act: -0.1700

Data Index: 5172072 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8321. Min Act: -0.1700

Data Index: 3411142 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.0144. Min Range: -5.0144

Max Act: 4.8417. Min Act: -0.1700

Data Index: 5799076 (Open Web Text)

Max Activating Token Index: 3