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

Dataset: Open Web Text

Neuron 702 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: 5.0812. Min Range: -5.0812

Max Act: 5.0812. Min Act: -0.1700

Data Index: 7412803 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.0812. Min Range: -5.0812

Max Act: 5.0584. Min Act: -0.1700

Data Index: 6482230 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.0812. Min Range: -5.0812

Max Act: 5.0366. Min Act: -0.1700

Data Index: 8016012 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.0812. Min Range: -5.0812

Max Act: 5.0521. Min Act: -0.1700

Data Index: 1795030 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.0812. Min Range: -5.0812

Max Act: 5.0449. Min Act: -0.1700

Data Index: 3329313 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9997. Min Act: -0.1700

Data Index: 7848303 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 5.0812. Min Range: -5.0812

Max Act: 5.0229. Min Act: -0.1700

Data Index: 7654367 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9969. Min Act: -0.1700

Data Index: 2992661 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9969. Min Act: -0.1700

Data Index: 3552686 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.0812. Min Range: -5.0812

Max Act: 5.0024. Min Act: -0.1700

Data Index: 6368736 (Open Web Text)

Max Activating Token Index: 888

Text #10

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9916. Min Act: -0.1700

Data Index: 7438087 (Open Web Text)

Max Activating Token Index: 820

Text #11

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9679. Min Act: -0.1700

Data Index: 2208209 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9536. Min Act: -0.1700

Data Index: 3248177 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9419. Min Act: -0.1700

Data Index: 6710212 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9518. Min Act: -0.1700

Data Index: 3283726 (Open Web Text)

Max Activating Token Index: 40

Text #15

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9486. Min Act: -0.1700

Data Index: 7186851 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9496. Min Act: -0.1700

Data Index: 7213163 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9884. Min Act: -0.1700

Data Index: 7382683 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9662. Min Act: -0.1700

Data Index: 3947300 (Open Web Text)

Max Activating Token Index: 31

Text #19

Max Range: 5.0812. Min Range: -5.0812

Max Act: 4.9521. Min Act: -0.1700

Data Index: 5367917 (Open Web Text)

Max Activating Token Index: 5