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

Dataset: Open Web Text

Neuron 2514 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: 3.0713. Min Range: -3.0713

Max Act: 3.0713. Min Act: -0.1700

Data Index: 7621178 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0656. Min Act: -0.1700

Data Index: 4760624 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0553. Min Act: -0.1700

Data Index: 4423730 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0612. Min Act: -0.1700

Data Index: 3744172 (Open Web Text)

Max Activating Token Index: 50

Text #4

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0402. Min Act: -0.1700

Data Index: 868849 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0518. Min Act: -0.1700

Data Index: 650181 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0504. Min Act: -0.1700

Data Index: 2874971 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0521. Min Act: -0.1700

Data Index: 6721840 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0560. Min Act: -0.1700

Data Index: 1137468 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0399. Min Act: -0.1700

Data Index: 3990825 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0304. Min Act: -0.1700

Data Index: 4861312 (Open Web Text)

Max Activating Token Index: 32

Text #11

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0369. Min Act: -0.1700

Data Index: 5102151 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0094. Min Act: -0.1700

Data Index: 1382607 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0203. Min Act: -0.1700

Data Index: 7019322 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0156. Min Act: -0.1700

Data Index: 6510967 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0118. Min Act: -0.1700

Data Index: 6048893 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0241. Min Act: -0.1700

Data Index: 5744064 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0149. Min Act: -0.1700

Data Index: 1619025 (Open Web Text)

Max Activating Token Index: 17

Text #18

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0115. Min Act: -0.1700

Data Index: 318244 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.0713. Min Range: -3.0713

Max Act: 3.0194. Min Act: -0.1700

Data Index: 5058368 (Open Web Text)

Max Activating Token Index: 29