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

Dataset: Open Web Text

Neuron 2043 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: 3.6846. Min Range: -3.6846

Max Act: 3.6672. Min Act: -0.1700

Data Index: 6455180 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6846. Min Act: -0.1700

Data Index: 1404364 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6724. Min Act: -0.1700

Data Index: 8776254 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6839. Min Act: -0.1700

Data Index: 8349513 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6843. Min Act: -0.1700

Data Index: 7674742 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6352. Min Act: -0.1700

Data Index: 7385967 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6179. Min Act: -0.1700

Data Index: 8456247 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6416. Min Act: -0.1700

Data Index: 8599845 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6352. Min Act: -0.1700

Data Index: 2135614 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6320. Min Act: -0.1700

Data Index: 5089808 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6308. Min Act: -0.1700

Data Index: 5462699 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6320. Min Act: -0.1700

Data Index: 384162 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6517. Min Act: -0.1700

Data Index: 5931788 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6179. Min Act: -0.1700

Data Index: 6123354 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6249. Min Act: -0.1700

Data Index: 1357214 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6068. Min Act: -0.1700

Data Index: 6294131 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.5957. Min Act: -0.1700

Data Index: 6162332 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6008. Min Act: -0.1700

Data Index: 6155920 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6201. Min Act: -0.1700

Data Index: 1287171 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6071. Min Act: -0.1700

Data Index: 5443138 (Open Web Text)

Max Activating Token Index: 8