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

Dataset: Open Web Text

Neuron 1888 in Layer 1

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: 4.4616. Min Range: -4.4616

Max Act: 4.4616. Min Act: -0.1700

Data Index: 2519694 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.3863. Min Act: -0.1700

Data Index: 2611264 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.3567. Min Act: -0.1700

Data Index: 1627259 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2992. Min Act: -0.1700

Data Index: 1031668 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2894. Min Act: -0.1700

Data Index: 7450914 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2958. Min Act: -0.1700

Data Index: 8386128 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.3082. Min Act: -0.1700

Data Index: 4576842 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2881. Min Act: -0.1700

Data Index: 5739965 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2654. Min Act: -0.1700

Data Index: 714951 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2720. Min Act: -0.1700

Data Index: 6037230 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2582. Min Act: -0.1700

Data Index: 6287974 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2776. Min Act: -0.1700

Data Index: 6387386 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.3096. Min Act: -0.1700

Data Index: 4410967 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2448. Min Act: -0.1700

Data Index: 8308393 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2417. Min Act: -0.1700

Data Index: 5100691 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2311. Min Act: -0.1700

Data Index: 358717 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2265. Min Act: -0.1700

Data Index: 5755776 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2161. Min Act: -0.1700

Data Index: 1367839 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2234. Min Act: -0.1700

Data Index: 3808401 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2025. Min Act: -0.1700

Data Index: 7130940 (Open Web Text)

Max Activating Token Index: 1023